This guide explains how the _AugmentedIntelligence Minecraft Spigot plugin, bridge, Minecraft DQN, client controller, and MathNN neural policy fit together.<\/p>\n\n\n\n
Related documentation:<\/p>\n\n\n\n
[text] The recommended architecture for your current lab is:<\/p>\n\n\n\n [text] The practical target is:<\/p>\n\n\n\n [text] Location:<\/p>\n\n\n\n [text] Runtime command aliases:<\/p>\n\n\n\n [text] Required permission:<\/p>\n\n\n\n [text] The plugin runs on the Minecraft server. It is responsible for:<\/p>\n\n\n\n [text] It is not meant to run heavy neural training. Training belongs in _AI.<\/p>\n\n\n\n The bridge is inside _AI. It listens for the Spigot plugin and receives JSON-lines messages.<\/p>\n\n\n\n Useful commands:<\/p>\n\n\n\n [text] Minecraft DQN is inside _AI. It reads the latest Minecraft state, chooses actions, records transitions, and trains from rewards.<\/p>\n\n\n\n Useful commands:<\/p>\n\n\n\n [text] Client control lets DQN play through the Minecraft client running on EARTH.<\/p>\n\n\n\n Useful commands:<\/p>\n\n\n\n [text] Client control sends local keyboard\/mouse input to the Minecraft window. Movement actions hold their keys for movement_hold_ms so walking and sprinting feel continuous while _AI waits for the next server observation. The Spigot plugin still provides observations, rewards, wall\/collision sensors, safety events, arenas, goals, and replay logs.<\/p>\n\n\n\n MathNN is the in-process neural-network backend. RLAgentNet wraps it as a reusable DQN learner for agents such as Minecraft, driving, gaming FPS, and strategy.<\/p>\n\n\n\n Useful commands:<\/p>\n\n\n\n [text] MathNN brings:<\/p>\n\n\n\n [text] MathNN does not press keys. It decides actions. The client controller executes those actions.<\/p>\n\n\n\n Minecraft DQN can advance Executive Functions<\/strong> plan steps alongside low-level<\/p>\n\n\n\n motor actions. Setting a goal seeds a Minecraft-tagged plan (wall-guard, net on,<\/p>\n\n\n\n observe, vision status, etc.). Each train\/eval step advances one executive<\/p>\n\n\n\n step by default (setup\/safety only \u2014 nested train\/step from the planner is blocked).<\/p>\n\n\n\n [text] From the repo root:<\/p>\n\n\n\n [powershell] If Gradle is not on PATH, use the local Gradle launcher:<\/p>\n\n\n\n [powershell] The jar is written to:<\/p>\n\n\n\n [text] Copy that jar to JUPITER:<\/p>\n\n\n\n [text] Restart the Minecraft server after replacing the jar.<\/p>\n\n\n\n Build the Visual Studio project after native code changes. In this workspace the project is:<\/p>\n\n\n\n [text] The Minecraft client controller is included in the project as:<\/p>\n\n\n\n [text] For a focused bridge compile after editing Minecraft bridge code, use MSBuild’s selected-file target:<\/p>\n\n\n\n [powershell] Use the full Visual Studio build before shipping a complete _AI binary. The selected-file compile only proves that the bridge source compiles against the current project settings.<\/p>\n\n\n\n EARTH runs _AI and the Minecraft client.<\/p>\n\n\n\n Inside _AI:<\/p>\n\n\n\n [text] PowerShell as Administrator on EARTH:<\/p>\n\n\n\n [powershell] JUPITER runs the Minecraft\/Spigot server.<\/p>\n\n\n\n In:<\/p>\n\n\n\n [text] Set:<\/p>\n\n\n\n [yaml] Then restart the Minecraft server or run:<\/p>\n\n\n\n [text] Test from JUPITER:<\/p>\n\n\n\n [powershell] You want:<\/p>\n\n\n\n [text] The plugin config is generated at:<\/p>\n\n\n\n [text] The bridge section should point from JUPITER to EARTH:<\/p>\n\n\n\n [yaml] Important safety and action defaults:<\/p>\n\n\n\n [yaml] Keep these defaults conservative during early training:<\/p>\n\n\n\n [text] Only enable arena.allow-world-edit when you are ready for \/ai arena build<\/p>\n\n\n\n to place blocks in the world. Only enable safety.allow-return-to-memory when<\/p>\n\n\n\n you want action 92 to teleport a player to \/ai memory mark base.<\/p>\n\n\n\n [text] [text] Use integration fields as curriculum context, not as direct control. WorldGuard, GriefPrevention, Towny, Factions, Residence, and PlotSquared explain protected regions or claims. Vault, Jobs, Quests, mcMMO, Citizens, and MythicMobs can become reward or objective signals. Command observation is off by default; enable it only when you want metadata about allowlisted plugin commands included in bridge events.<\/p>\n\n\n\n [text] Current plugin-side action IDs:<\/p>\n\n\n\n [text] Actions 11 through 19 are client hotbar actions and only have an effect when _AI is controlling the Minecraft client. Action 92 is disabled by default. Enable:<\/p>\n\n\n\n [yaml] only if you want the plugin to teleport players to \/ai memory mark base.<\/p>\n\n\n\n Actions 94 and 95 require safety.allow-weather: true and<\/p>\n\n\n\n safety.allow-time: true. These stay disabled by default so training cannot<\/p>\n\n\n\n silently change server weather or time.<\/p>\n\n\n\n [text] Safety checks include:<\/p>\n\n\n\n [text] [text] Coach mode gives local survival advice and is useful during early training.<\/p>\n\n\n\n The plugin can forward player chat to _AI, where the configured LLM\/router generates a concise Minecraft chat reply. Each chat prompt includes the player message plus Minecraft context: health, food, biome, selected item, active goal, arena, safety state, nearby players, nearby hostiles, nearest memory, player preference, and recent transcript.<\/p>\n\n\n\n Default player usage:<\/p>\n\n\n\n [text] Core plugin controls:<\/p>\n\n\n\n [text] _AI bridge controls:<\/p>\n\n\n\n [text] Training use:<\/p>\n\n\n\n [text] With chat.require-mention=true, the bot only replies<\/strong> when a player uses !ai \/ @ai. With chat.listen-all=true (default), ordinary player chat is still read<\/strong>: it is stored in transcripts and passively forwarded to _AI for context (expect_reply=false), so the next mention can use recent server chat. Use \/ai chat mode listen for that setup, \/ai chat mode mention to ignore unmentioned chat entirely, or \/ai chat mode all to answer every line. Use chat.scope=private while training one player, nearby for small co-op testing, and global only for operator announcements.<\/p>\n\n\n\n [text] Memory markers are stored per player in:<\/p>\n\n\n\n [text] [text] Replay logs are JSONL files under:<\/p>\n\n\n\n [text] These logs are useful for offline training and debugging.<\/p>\n\n\n\n [text] Goal profiles currently include:<\/p>\n\n\n\n [text] [text] Quest commands choose a goal based on the player state.<\/p>\n\n\n\n [text] Follow mode is useful for guided data collection. Let the bot follow a real player through routes you want it to learn, keep replay logging enabled, then repeat the same area without follow mode during DQN training.<\/p>\n\n\n\n [text] The HUD shows training-relevant state in-game, including goal, arena, follow status, health, food, held item, target block, and position.<\/p>\n\n\n\n [text] The curriculum runner creates\/starts phase arenas and applies the matching goal profile. Teaching commands write replay records and send small reward\/correction events. Metrics track action distribution, repeated-action loops, reward totals, death snapshots, and dashboard export data.<\/p>\n\n\n\n The \/ai ml commands add lightweight server-side models around that data. They do not replace the DQN or MathNN learner in _AI; they provide live summaries and bridge requests:<\/p>\n\n\n\n [text] [text] By default, arena creation only records an arena marker. It does not edit blocks.<\/p>\n\n\n\n The command below edits the world only if enabled:<\/p>\n\n\n\n [text] To enable block editing:<\/p>\n\n\n\n [yaml] Keep this off until you are ready to let the plugin place floor\/fence\/torch blocks.<\/p>\n\n\n\n Use flat for first movement tests, wall and hallway for stuck recovery, steps and pit for jump timing, bridge for block placement and path correction, and obstacle for mixed navigation.<\/p>\n\n\n\n [text] Kits are training aids for controlled sessions. path reports why forward,<\/p>\n\n\n\n left, right, or back is blocked from the player’s current yaw. route measures<\/p>\n\n\n\n distance between two memory markers in the same world. mob spawn is for<\/p>\n\n\n\n controlled survival-pressure tests; keep counts low and use arenas.<\/p>\n\n\n\n [text] Meanings:<\/p>\n\n\n\n [text] [text] step does one RL cycle:<\/p>\n\n\n\n [text] Use step for early testing.<\/p>\n\n\n\n [text] train [interval_ms] starts a background loop that repeatedly runs step.<\/p>\n\n\n\n Stop it with:<\/p>\n\n\n\n [text] or:<\/p>\n\n\n\n [text] Change the delay:<\/p>\n\n\n\n [text] Check whether it is running:<\/p>\n\n\n\n [text] Look for:<\/p>\n\n\n\n [text] [text] Actions are sent to the Spigot bridge or RCON. This is useful for server automation and safe allowlisted actions.<\/p>\n\n\n\n [text] Actions are sent as keyboard\/mouse input to your local Minecraft client on EARTH.<\/p>\n\n\n\n Client action mapping:<\/p>\n\n\n\n [text] Useful client commands:<\/p>\n\n\n\n [text] Recommended for client control:<\/p>\n\n\n\n [text] When wall_guard=on, DQN avoids choosing client movement actions that the plugin reports as blocked. Blocked movement attempts are also penalized in the reward function so the policy learns to turn, back up, strafe, jump, or attack instead of holding forward into a wall.<\/p>\n\n\n\n minecraft dqn client hold <milliseconds> controls how long movement keys stay down for forward, back, strafe, and sprint actions. Sprint holds W plus left control for this duration. minecraft dqn client mine-hold <milliseconds> controls how long the left mouse button is held for the client_mine_hold action, which is what lets the DQN break blocks instead of only tapping attack. minecraft dqn client use-hold <milliseconds> controls how long right mouse is held for the client_place_hold action. Use minecraft dqn client mine or minecraft dqn client action 9 to manually test mining, minecraft dqn client place or minecraft dqn client action 10 to manually test right-click block placement\/use, and minecraft dqn client slot <1-9> to test hotbar selection. Use minecraft dqn client release if you ever need to force held movement or mouse input up.<\/p>\n\n\n\n Server-side movement actions can be smoothed by the Spigot plugin instead of teleporting one block at a time:<\/p>\n\n\n\n [text] Additional plugin features:<\/p>\n\n\n\n [text] The plugin observation includes target block, target distance\/hardness, placeable-face, hotbar slot, selected item count, inventory tool flags, food\/block availability, wood\/cobblestone\/torch counts, yaw\/pitch, and local block-grid signals. These fields give the DQN enough context to learn when to mine, place, switch hotbar slots, jump, or turn.<\/p>\n\n\n\n [text] This sends client actions and server actions. Use this only for debugging because it can double-apply effects.<\/p>\n\n\n\n Enable MathNN-backed neural DQN:<\/p>\n\n\n\n [text] Save\/load:<\/p>\n\n\n\n [text] MathNN is useful because it can learn a state-to-Q-values function:<\/p>\n\n\n\n [text] That lets the agent generalize across similar states. The built-in compact DQN can work for smoke tests, but MathNN is the better long-term backend.<\/p>\n\n\n\n Recommended MathNN workflow:<\/p>\n\n\n\n [text] Use this sequence when starting fresh.<\/p>\n\n\n\n [text] [text] If dry-run looks sane:<\/p>\n\n\n\n [text] Then run single steps:<\/p>\n\n\n\n [text] Repeat manually 10 to 20 times.<\/p>\n\n\n\n If it behaves safely:<\/p>\n\n\n\n [text] Stop it:<\/p>\n\n\n\n [text] Train one behavior at a time. Do not start in open survival and expect useful learning: the action space includes movement, camera control, mining, placing, and hotbar selection, so the early reward signal must be simple and repeatable.<\/p>\n\n\n\n Use this rule for promotion:<\/p>\n\n\n\n [text] Use this rule for rollback:<\/p>\n\n\n\n [text] Run this at the start of every training session.<\/p>\n\n\n\n In Minecraft:<\/p>\n\n\n\n [text] In _AI:<\/p>\n\n\n\n [text] Use MathNN once the basic loop is stable:<\/p>\n\n\n\n [text] Keep training windows short. Start with minecraft dqn train 1000, stop after 2 to 5 minutes, inspect behavior, then continue. Faster intervals such as 250 or 500 are useful only after observations are clearly updating and the client is responding correctly.<\/p>\n\n\n\n Goal:<\/p>\n\n\n\n [text] Commands:<\/p>\n\n\n\n [text] Watch for:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] Commands:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] If movement is choppy, raise the hold time:<\/p>\n\n\n\n [text] If mining only taps, raise the mine hold:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] In Minecraft:<\/p>\n\n\n\n [text] In _AI:<\/p>\n\n\n\n [text] Run 10 to 20 manual steps first. Then:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] Save a baseline checkpoint:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] Use a simple wall first:<\/p>\n\n\n\n [text] Then use a hallway:<\/p>\n\n\n\n [text] In _AI:<\/p>\n\n\n\n [text] Watch for:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] Use steps first:<\/p>\n\n\n\n [text] Then use a pit:<\/p>\n\n\n\n [text] Train slowly:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] Manual setup:<\/p>\n\n\n\n [text] Commands:<\/p>\n\n\n\n [text] Watch for:<\/p>\n\n\n\n [text] Promote when:<\/p>\n\n\n\n [text] Goal:<\/p>\n\n\n\n [text] Manual setup:<\/p>\n\n\n\n [text] Commands:<\/p>\n\n\n\n
<\/em>docs\/MinecraftPluginOperations.md = quick operator reference, full command list, config switches, troubleshooting
docs\/MinecraftIntegration.md = bridge vs. RCON integration overview
docs\/ReinforcementLearning.md = RL hub (MathNN, curriculum, executive plans)
docs\/MathNN.md = neural policy modes and rl net commands
minecraft_spigot_plugin\/README.md = plugin build\/deploy quick reference<\/p>\n\n\n\n
<\/em>EARTH 10.0.0.151 = _AI host, Minecraft client, DQN, optional MathNN
JUPITER 10.0.0.153 = Minecraft\/Spigot server, AI bridge plugin
NEPTUNE = optional always-on AI\/training server later<\/p>\n\n\n\n
<\/em>JUPITER plugin observes world\/player state
JUPITER plugin sends rewards\/events to _AI
_AI DQN\/MathNN chooses an action
EARTH client controller presses keys\/mouse in your Minecraft client
JUPITER plugin keeps providing safety, arena, goal, and replay data<\/p>\n\n\n\nComponents<\/h2>\n\n\n\n
Spigot Plugin<\/h3>\n\n\n\n
<\/em>minecraft_spigot_plugin\/<\/p>\n\n\n\n
<\/em>\/ai
\/aibridge<\/p>\n\n\n\n
<\/em>augmentedintelligence.admin<\/p>\n\n\n\n
<\/em>observations
events and rewards
safety checks
training arenas
goal profiles
coach mode
memory markers
replay logging
manual safe actions
optional context from common Spigot plugins such as Vault, WorldGuard, Citizens, Jobs, Quests, Towny, Factions, mcMMO, CoreProtect, PlotSquared, and BentoBox<\/p>\n\n\n\nNative Bridge<\/h3>\n\n\n\n
<\/em>minecraft bridge configure 0.0.0.0 8765 YOUR_TOKEN true
minecraft bridge start
minecraft bridge status
minecraft bridge stop<\/p>\n\n\n\nMinecraft DQN<\/h3>\n\n\n\n
<\/em>minecraft dqn status
minecraft dqn player YourMinecraftName
minecraft dqn observe
minecraft dqn eval
minecraft dqn step
minecraft dqn train 1000
minecraft dqn off<\/p>\n\n\n\nClient Controller<\/h3>\n\n\n\n
<\/em>minecraft dqn control client
minecraft dqn client status
minecraft dqn client focus on
minecraft dqn client foreground on
minecraft dqn client hold 900
minecraft dqn client mine-hold 1800
minecraft dqn client use-hold 350
minecraft dqn client mine
minecraft dqn client place
minecraft dqn client slot 1
minecraft dqn client look-up
minecraft dqn unstuck on
minecraft dqn wall-guard status<\/p>\n\n\n\nMathNN \/ RLAgentNet<\/h3>\n\n\n\n
<\/em>minecraft dqn net on
minecraft dqn net status
minecraft dqn net save minecraft_mathnn_checkpoint.txt
minecraft dqn net load minecraft_mathnn_checkpoint.txt<\/p>\n\n\n\n
<\/em>neural Q-value prediction
better generalization than simple tables or tiny hardcoded models
shared RL infrastructure
save\/load checkpoints
future offline replay training
metrics such as loss and observe count<\/p>\n\n\n\nExecutive Functions planner (high-level steps)<\/h3>\n\n\n\n
<\/em>minecraft dqn plan on
minecraft dqn goal mine iron_ore
minecraft dqn plan detail
minecraft dqn plan next 2
minecraft dqn train 1000
minecraft dqn plan status
minecraft dqn plan steps 1
minecraft dqn plan off<\/p>\n\n\n\nBuild<\/h2>\n\n\n\n
Build The Spigot Plugin<\/h3>\n\n\n\n
<\/em>cd minecraft_spigot_plugin
gradle jar<\/p>\n\n\n\n
<\/em>.\\gradle\\bin\\gradle.bat jar<\/p>\n\n\n\n
<\/em>minecraft_spigot_plugin\/build\/libs\/AugmentedIntelligenceSpigotBridge-2.0.0.jar<\/p>\n\n\n\n
<\/em><minecraft-server>\/plugins\/<\/p>\n\n\n\nBuild _AI<\/h3>\n\n\n\n
<\/em>_AugmentedIntelligence.vcxproj<\/p>\n\n\n\n
<\/em>MinecraftClientController.cpp
MinecraftClientController.hpp<\/p>\n\n\n\n
<\/em>& “C:\\Program Files\\Microsoft Visual Studio\\18\\Community\\MSBuild\\Current\\Bin\\MSBuild.exe” `
_AugmentedIntelligence.vcxproj `
\/p:Configuration=Debug `
\/p:Platform=x64 `
\/t:ClCompile `
\/p:SelectedFiles=MinecraftSpigotBridge.cpp `
\/p:CL_MPCount=1<\/p>\n\n\n\nNetwork Setup<\/h2>\n\n\n\n
EARTH<\/h3>\n\n\n\n
<\/em>minecraft bridge configure 0.0.0.0 8765 YOUR_LONG_SHARED_TOKEN true
minecraft bridge start
minecraft bridge status<\/p>\n\n\n\n
<\/em>Remove-NetFirewallRule -DisplayName “AI Spigot Bridge 8765 from JUPITER” -ErrorAction SilentlyContinue
New-NetFirewallRule `
-DisplayName “AI Spigot Bridge 8765 from JUPITER” `
-Direction Inbound `
-Protocol TCP `
-LocalPort 8765 `
-RemoteAddress 10.0.0.153 `
-Action Allow `
-Profile Any<\/p>\n\n\n\nJUPITER<\/h3>\n\n\n\n
<\/em>plugins\/AugmentedIntelligenceBridge\/config.yml<\/p>\n\n\n\n
<\/em>bridge:
host: “10.0.0.151”
port: 8765
token: “YOUR_LONG_SHARED_TOKEN”
server-id: “jupiter-survival”<\/p>\n\n\n\n
<\/em>\/ai reload
\/ai connect
\/ai status<\/p>\n\n\n\n
<\/em>Test-NetConnection 10.0.0.151 -Port 8765<\/p>\n\n\n\n
<\/em>TcpTestSucceeded : True<\/p>\n\n\n\nPlugin Configuration Reference<\/h2>\n\n\n\n
<\/em>plugins\/AugmentedIntelligenceBridge\/config.yml<\/p>\n\n\n\n
<\/em>bridge:
host: “10.0.0.151”
port: 8765
token: “YOUR_LONG_SHARED_TOKEN”
server-id: “jupiter-survival”
reconnect-seconds: 5
observation-period-ticks: 20
send-all-players: true
primary-player: “”<\/p>\n\n\n\n
<\/em>safety:
enabled: true
block-unsafe-ai-actions: true
allow-teleport-nudges: true
allow-effects: true
allow-weather: false
allow-time: false
allow-save: true
allow-return-to-memory: false
restrict-build-to-arena: false
actions:
dry-run: false
smooth-server-movement: true
smooth-move-ticks: 8
smooth-move-speed: 0.28
sneak-ticks: 30<\/p>\n\n\n\n
<\/em>safety.enabled=true
safety.allow-return-to-memory=false
safety.allow-weather=false
safety.allow-time=false
arena.allow-world-edit=false
chat.require-mention=true
chat.listen-all=true
chat.listen-forward=true<\/p>\n\n\n\nPlugin Commands<\/h2>\n\n\n\n
Bridge<\/h3>\n\n\n\n
<\/em>\/ai help
\/ai status
\/ai connect
\/ai disconnect
\/ai reload
\/ai observe
\/ai monitor
\/ai debug [player]
\/ai explain [player]<\/p>\n\n\n\nPlugin Integrations<\/h3>\n\n\n\n
<\/em>\/ai integrations status
\/ai integrations scan
\/ai integrations list
\/ai integrations payload [player]
\/ai integrations observe on|off
\/ai integrations events on|off
\/ai integrations commands on|off
\/ai integrations args on|off<\/p>\n\n\n\nManual Actions<\/h3>\n\n\n\n
<\/em>\/ai action <id> [player]
\/ai dryrun on
\/ai dryrun off
\/ai qvalues [player]<\/p>\n\n\n\n
<\/em>0 observe
1 smooth_forward
2 smooth_back
3 smooth_strafe_left
4 smooth_strafe_right
5 jump
6 smooth_sprint_forward
7 turn_left
8 turn_right
9 break_target_block
10 place_target_block
11 client_hotbar_1
12 client_hotbar_2
13 client_hotbar_3
14 client_hotbar_4
15 client_hotbar_5
16 client_hotbar_6
17 client_hotbar_7
18 client_hotbar_8
19 client_hotbar_9
20 smooth_jump_forward
21 smooth_jump_sprint_forward
22 smooth_forward_left
23 smooth_forward_right
24 look_up
25 look_down
26 sneak
27 swim_up
28 swim_down
29 eat_food
30 select_best_tool
31 place_torch
32 equip_shield
33 use_item
34 open_close_door
35 look_at_nearest_hostile
36 look_at_nearest_item
37 look_at_nearest_player
38 pickup_nearest_item
39 craft_basic_tools
40 smelt_ore
41 sleep_at_night
42 return_safe_zone
43 return_arena_center
90 retreat
91 extinguish
92 return_to_base
93 coach_ping
94 clear_weather
95 set_day
96 save_world<\/p>\n\n\n\n
<\/em>safety:
allow-return-to-memory: true<\/p>\n\n\n\nSafety<\/h3>\n\n\n\n
<\/em>\/ai safety
\/ai safety on
\/ai safety off
\/ai safety build-zone on
\/ai safety build-zone off<\/p>\n\n\n\n
<\/em>low health
low food
nearby hostiles
near lava
fall risk
burning
dead player<\/p>\n\n\n\nCoach<\/h3>\n\n\n\n
<\/em>\/ai coach on
\/ai coach off
\/ai coach status
\/ai coach explain [player]
\/ai explain [player]<\/p>\n\n\n\nLLM Chat<\/h3>\n\n\n\n
<\/em>!ai what should I do next?
@ai where is base?<\/p>\n\n\n\n
<\/em>\/ai chat status
\/ai chat on
\/ai chat off
\/ai chat trigger !ai
\/ai chat mention @ai
\/ai chat require-mention on
\/ai chat scope private
\/ai chat scope nearby
\/ai chat scope team
\/ai chat scope global
\/ai chat cooldown 3
\/ai chat model llama3
\/ai chat system survival_coach
\/ai chat ask what should I do next?
\/ai chat transcript YourPlayer 12
\/ai chat clear-memory YourPlayer
\/ai chat mute PlayerName
\/ai chat unmute PlayerName
\/ai chat preference YourPlayer short tactical survival advice
\/ai chat metrics<\/p>\n\n\n\n
<\/em>minecraft bridge chat status
minecraft bridge chat metrics
minecraft bridge chat on
minecraft bridge chat off
minecraft bridge chat cooldown 3
minecraft bridge chat model llama3
minecraft bridge chat system survival_coach
minecraft bridge chat clear YourPlayer
minecraft bridge chat say @a hello from _AI<\/p>\n\n\n\n
<\/em>!ai collect wood
!ai mine iron
!ai return to base
!ai survive
!ai start flatwalk training
!ai next phase
!ai good
!ai bad
!ai try turn left when blocked
!ai remember this as base
!ai what happened last run
!ai why did you do that<\/p>\n\n\n\nMemory<\/h3>\n\n\n\n
<\/em>\/ai memory mark base
\/ai memory mark mine
\/ai memory mark village
\/ai memory list
\/ai memory nearest
\/ai memory remove base<\/p>\n\n\n\n
<\/em>plugins\/AugmentedIntelligenceBridge\/memory.yml<\/p>\n\n\n\nReplay Logging<\/h3>\n\n\n\n
<\/em>\/ai replay start
\/ai replay status
\/ai replay stop
\/ai replay file
\/ai replay export<\/p>\n\n\n\n
<\/em>plugins\/AugmentedIntelligenceBridge\/replay\/<\/p>\n\n\n\nGoals<\/h3>\n\n\n\n
<\/em>\/ai goal list
\/ai goal set survive_60 [player]
\/ai goal set mob_avoidance [player]
\/ai goal set collect_wood [player]
\/ai goal set mine_iron [player]
\/ai goal set return_to_base [player]
\/ai goal status [player]
\/ai goal clear [player]
\/ai goal suggest [player]<\/p>\n\n\n\n
<\/em>survive_60
mob_avoidance
collect_wood
mine_iron
return_to_base<\/p>\n\n\n\nQuests<\/h3>\n\n\n\n
<\/em>\/ai quest suggest [player]
\/ai quest start [player]<\/p>\n\n\n\nFollow Mode<\/h3>\n\n\n\n
<\/em>\/ai follow <target-player> [follower]
\/ai follow stop [follower]
\/ai follow status [follower]<\/p>\n\n\n\nHUD<\/h3>\n\n\n\n
<\/em>\/ai hud on
\/ai hud off
\/ai hud status<\/p>\n\n\n\nCurriculum, Teaching, And Metrics<\/h3>\n\n\n\n
<\/em>\/ai curriculum list
\/ai curriculum start [phase] [player]
\/ai curriculum next [player]
\/ai curriculum reset [player]
\/ai curriculum stop [player]
\/ai curriculum status [player]
\/ai teach start [player]
\/ai teach stop [player]
\/ai teach good [note] [player]
\/ai teach bad [note] [player]
\/ai teach try <hint> [player]
\/ai metrics status [player]
\/ai metrics actions [player]
\/ai metrics reward [player]
\/ai metrics recent [player]
\/ai metrics prometheus
\/ai metrics export
\/ai metrics dashboard
\/ai ml status [player]
\/ai ml systems
\/ai ml train replay
\/ai ml behavior [player]
\/ai ml bc [player]
\/ai ml reward [player]
\/ai ml stuck [player]
\/ai ml nav [player]
\/ai ml planner [player]
\/ai ml player [player]
\/ai ml coach [player]
\/ai ml death [player]
\/ai ml roles
\/ai ml anomaly
\/ai ml grief [player]
\/ai ml memory [player]
\/ai ml mathnn [player]
\/ai ml vision request [player]
\/ai ml quest [player]
\/ai ml council [player]
\/ai ml export
\/ai ml dashboard<\/p>\n\n\n\n
<\/em>replay trainer = scans bounded replay JSONL files and summarizes observations\/actions\/events
behavior cloning = counts demonstrated and successful actions into action priors
reward model = summarizes events, rewards, and teach good\/bad feedback
stuck classifier = detects low-motion and blocked-direction states
navigability model = scores forward\/left\/right\/back and terrain signatures
hierarchical planner = chooses a local plan from safety, stuck state, goal, and memory
player model = tracks chat intent, preferences, rough skills, spam\/toxicity signals
roles\/council = suggests miner\/builder\/guard\/coach\/explorer roles for online players
anomaly\/grief = watches server tick timing and rapid block edits outside arenas
coach\/death = sends structured bridge requests for LLM session coaching and death review
mathnn\/vision = sends bridge requests for `_AI`\/EARTH-side neural or screenshot systems<\/p>\n\n\n\nArenas<\/h3>\n\n\n\n
<\/em>\/ai arena create survival 12
\/ai arena start survival survive_60 YourMinecraftName
\/ai arena status YourMinecraftName
\/ai arena reset YourMinecraftName
\/ai arena stop YourMinecraftName<\/p>\n\n\n\n
<\/em>\/ai arena build survival flat
\/ai arena build survival hallway
\/ai arena build survival wall
\/ai arena build survival steps
\/ai arena build survival bridge
\/ai arena build survival pit
\/ai arena build survival obstacle
\/ai arena build survival random<\/p>\n\n\n\n
<\/em>arena:
allow-world-edit: true<\/p>\n\n\n\nOperator Utilities<\/h3>\n\n\n\n
<\/em>\/ai kit miner [player]
\/ai kit builder [player]
\/ai kit survival [player]
\/ai kit torch [player]
\/ai kit clear [player]
\/ai path [player]
\/ai route <from-marker> <to-marker> [player]
\/ai mob spawn <zombie|skeleton|spider|creeper> [count] [player]<\/p>\n\n\n\nDQN Commands<\/h2>\n\n\n\n
Observation and Planning<\/h3>\n\n\n\n
<\/em>minecraft dqn status
minecraft dqn player YourMinecraftName
minecraft dqn observe
minecraft dqn eval
minecraft dqn dry-run
minecraft dqn qvalues
minecraft dqn explain 10<\/p>\n\n\n\n
<\/em>observe = read latest state
eval = choose\/check current policy mode
dry-run = choose action without sending it
qvalues = show the compact DQN’s top legal action values
explain = show planned action plus top legal Q-values<\/p>\n\n\n\nSingle-Step Training<\/h3>\n\n\n\n
<\/em>minecraft dqn step<\/p>\n\n\n\n
<\/em>observe current state
choose one action
send that action
observe next state
collect reward\/event feedback
store transition
train once if mode=train
stop<\/p>\n\n\n\nAutonomous Training<\/h3>\n\n\n\n
<\/em>minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>minecraft dqn off<\/p>\n\n\n\n
<\/em>minecraft dqn eval
minecraft dqn observe<\/p>\n\n\n\n
<\/em>minecraft dqn interval 2000<\/p>\n\n\n\n
<\/em>minecraft dqn status<\/p>\n\n\n\n
<\/em>mode=train
auto_train=running<\/p>\n\n\n\nControl Modes<\/h2>\n\n\n\n
Server Control<\/h3>\n\n\n\n
<\/em>minecraft dqn control server<\/p>\n\n\n\nClient Control<\/h3>\n\n\n\n
<\/em>minecraft dqn control client<\/p>\n\n\n\n
<\/em>0 observe
1 W \/ forward
2 S \/ back
3 A \/ strafe left
4 D \/ strafe right
5 space \/ jump
6 ctrl+W \/ sprint forward
7 mouse turn left
8 mouse turn right
9 left click \/ attack
10 right click \/ use or place
11 hotbar slot 1
12 hotbar slot 2
13 hotbar slot 3
14 hotbar slot 4
15 hotbar slot 5
16 hotbar slot 6
17 hotbar slot 7
18 hotbar slot 8
19 hotbar slot 9
20 W+space \/ jump forward
21 ctrl+W+space \/ sprint jump forward
22 W+A \/ forward left
23 W+D \/ forward right
24 mouse look up
25 mouse look down<\/p>\n\n\n\n
<\/em>minecraft dqn client status
minecraft dqn client focus on
minecraft dqn client foreground on
minecraft dqn client title Minecraft
minecraft dqn client hold 900
minecraft dqn client mine-hold 1800
minecraft dqn client use-hold 350
minecraft dqn client mine
minecraft dqn client action 9
minecraft dqn client place
minecraft dqn client action 10
minecraft dqn client release
minecraft dqn wall-guard on
minecraft dqn wall-guard status<\/p>\n\n\n\n
<\/em>Minecraft window open on EARTH
Minecraft connected to JUPITER
Minecraft window in foreground
_AI running on EARTH
Spigot bridge connected
wall_guard=on
movement_hold_ms=900<\/p>\n\n\n\n
<\/em>\/ai movement status
\/ai movement smooth on
\/ai movement ticks 8
\/ai movement speed 0.28<\/p>\n\n\n\n
<\/em>\/ai follow <target-player> [follower]
\/ai hud on
\/ai safety build-zone on
\/ai replay file
\/ai arena build <name> hallway|wall|steps|bridge|pit|obstacle<\/p>\n\n\n\nHybrid Control<\/h3>\n\n\n\n
<\/em>minecraft dqn control both<\/p>\n\n\n\nMathNN Training<\/h2>\n\n\n\n
<\/em>minecraft dqn net on
minecraft dqn net status<\/p>\n\n\n\n
<\/em>minecraft dqn net save minecraft_mathnn_checkpoint.txt
minecraft dqn net load minecraft_mathnn_checkpoint.txt<\/p>\n\n\n\n
<\/em>state -> Q(action 0), Q(action 1), … Q(action N)<\/p>\n\n\n\n
<\/em>1. Run plugin replay logging.
2. Train with single-step DQN in a controlled arena.
3. Enable MathNN with minecraft dqn net on.
4. Run short autonomous training windows.
5. Save checkpoints after stable behavior.
6. Later, train offline on NEPTUNE from replay logs.<\/p>\n\n\n\nFirst Safe Training Run<\/h2>\n\n\n\n
In Minecraft<\/h3>\n\n\n\n
<\/em>\/ai status
\/ai safety
\/ai coach on
\/ai memory mark base
\/ai replay start
\/ai dryrun on
\/ai arena create survival 12
\/ai arena start survival survive_60 YourMinecraftName
\/ai goal status YourMinecraftName<\/p>\n\n\n\nIn _AI<\/h3>\n\n\n\n
<\/em>minecraft bridge status
minecraft dqn player YourMinecraftName
minecraft dqn control client
minecraft dqn client status
minecraft dqn client focus on
minecraft dqn client hold 900
minecraft dqn client mine-hold 1800
minecraft dqn client use-hold 350
minecraft dqn client mine
minecraft dqn client place
minecraft dqn observe
minecraft dqn dry-run<\/p>\n\n\n\n
<\/em>\/ai dryrun off<\/p>\n\n\n\n
<\/em>minecraft dqn step
minecraft dqn status<\/p>\n\n\n\n
<\/em>minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>minecraft dqn off<\/p>\n\n\n\nTraining Curriculum<\/h2>\n\n\n\n
<\/em>Promote only when the agent completes the current phase 3 runs in a row without death, safety intervention, or repeated wall pushing.<\/p>\n\n\n\n
<\/em>If the agent dies twice in 10 minutes or gets stuck for more than 30 seconds, stop training, reset the arena, and go back one phase.<\/p>\n\n\n\nStandard Session Setup<\/h3>\n\n\n\n
<\/em>\/ai status
\/ai safety on
\/ai coach on
\/ai hud on
\/ai replay start
\/ai memory mark base
\/ai integrations status<\/p>\n\n\n\n
<\/em>minecraft bridge status
minecraft dqn player YourMinecraftName
minecraft dqn control client
minecraft dqn client focus on
minecraft dqn client hold 900
minecraft dqn client mine-hold 1800
minecraft dqn client use-hold 350
minecraft dqn wall-guard on
minecraft dqn unstuck on
minecraft dqn observe
minecraft dqn status<\/p>\n\n\n\n
<\/em>minecraft dqn net on
minecraft dqn net status<\/p>\n\n\n\nPhase 0: Bridge And Sensor Baseline<\/h3>\n\n\n\n
<\/em>prove the plugin, bridge, observations, rewards, and replay logging work before learning starts<\/p>\n\n\n\n
<\/em>\/ai observe
\/ai debug YourMinecraftName
minecraft bridge status
minecraft dqn observe
minecraft dqn dry-run<\/p>\n\n\n\n
<\/em>connected=yes
observations increasing
health and food correct
target_block_type present
hotbar_slot present
blocked={…} present
plugin_integrations_count present<\/p>\n\n\n\n
<\/em>three consecutive observe calls show fresh state
dry-run selects an action without sending it
replay logging is active<\/p>\n\n\n\nPhase 1: Manual Client Calibration<\/h3>\n\n\n\n
<\/em>prove every physical input works through your Minecraft client on EARTH<\/p>\n\n\n\n
<\/em>minecraft dqn control client
minecraft dqn client status
minecraft dqn client focus on
minecraft dqn client action 1
minecraft dqn client action 6
minecraft dqn client action 7
minecraft dqn client action 8
minecraft dqn client action 20
minecraft dqn client action 21
minecraft dqn client look-up
minecraft dqn client look-down
minecraft dqn client slot 1
minecraft dqn client slot 2
minecraft dqn client mine
minecraft dqn client place
minecraft dqn client release<\/p>\n\n\n\n
<\/em>forward and sprint move smoothly
turn actions rotate the camera
look up\/down changes pitch
hotbar slots change
left mouse holds long enough to break a soft block
right mouse places or uses the held item<\/p>\n\n\n\n
<\/em>minecraft dqn client hold 1100<\/p>\n\n\n\n
<\/em>minecraft dqn client mine-hold 2400<\/p>\n\n\n\nPhase 2: Flat Arena Locomotion<\/h3>\n\n\n\n
<\/em>learn that forward, turn, strafe, jump, and sprint affect position without danger<\/p>\n\n\n\n
<\/em>\/ai arena create flatwalk 12
\/ai arena build flatwalk flat
\/ai arena start flatwalk survive_60 YourMinecraftName
\/ai goal set survive_60 YourMinecraftName<\/p>\n\n\n\n
<\/em>minecraft dqn observe
minecraft dqn step
minecraft dqn status<\/p>\n\n\n\n
<\/em>minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>the player moves around the arena instead of idling
health remains stable
blocked movement is rare
no death or safety intervention occurs for 3 short runs<\/p>\n\n\n\n
<\/em>minecraft dqn save
minecraft dqn net save minecraft_phase02_flatwalk.txt<\/p>\n\n\n\nPhase 3: Wall And Hallway Recovery<\/h3>\n\n\n\n
<\/em>learn not to hold forward into walls and learn to turn, back up, strafe, jump, or mine when blocked<\/p>\n\n\n\n
<\/em>\/ai arena create walltest 10
\/ai arena build walltest wall
\/ai arena start walltest survive_60 YourMinecraftName
\/ai goal set survive_60 YourMinecraftName<\/p>\n\n\n\n
<\/em>\/ai arena create hallway 12
\/ai arena build hallway hallway
\/ai arena start hallway survive_60 YourMinecraftName<\/p>\n\n\n\n
<\/em>minecraft dqn wall-guard on
minecraft dqn unstuck on
minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>blocked_forward changing correctly
turn_left or turn_right after blocked_forward
back, strafe, jump_forward, or break_target_block when blocked
stuck_ticks staying low in minecraft dqn status<\/p>\n\n\n\n
<\/em>the agent recovers from a wall contact within 5 seconds
it does not repeatedly press forward into the same wall
it can travel through the hallway for 3 runs without manual rescue<\/p>\n\n\n\nPhase 4: Jump Timing And Uneven Terrain<\/h3>\n\n\n\n
<\/em>learn jump_forward, sprint_jump_forward, pitch control, and recovery around ledges<\/p>\n\n\n\n
<\/em>\/ai arena create steps 12
\/ai arena build steps steps
\/ai arena start steps survive_60 YourMinecraftName<\/p>\n\n\n\n
<\/em>\/ai arena create pit 12
\/ai arena build pit pit
\/ai arena start pit survive_60 YourMinecraftName<\/p>\n\n\n\n
<\/em>minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>the agent climbs simple steps
the agent avoids repeatedly falling into the pit
fall-risk safety events are rare
the agent uses jump_forward or sprint_jump_forward when elevation changes<\/p>\n\n\n\nPhase 5: Target Block Mining<\/h3>\n\n\n\n
<\/em>learn when looking at a breakable block should trigger mining instead of movement<\/p>\n\n\n\n
<\/em>put a wooden, dirt, stone, or low-hardness target block inside the arena
put the correct tool in hotbar slot 1 or slot 2
face the player toward the target block<\/p>\n\n\n\n
<\/em>minecraft dqn client slot 1
minecraft dqn client mine
minecraft dqn observe
\/ai goal set collect_wood YourMinecraftName
minecraft dqn train 1000<\/p>\n\n\n\n
<\/em>target_block_type is not air
target_block_breakable=true
target_block_distance is reasonable
has_pickaxe or has_axe is true when the tool is carried
block_break events appear in replay logs<\/p>\n\n\n\n
<\/em>the agent breaks visible soft blocks reliably
it does not mine air for long periods
it switches away from movement when a useful target block is directly in front<\/p>\n\n\n\nPhase 6: Block Placement And Bridging<\/h3>\n\n\n\n
<\/em>learn hotbar selection, right-click placement, and correction around gaps<\/p>\n\n\n\n
<\/em>put blocks in hotbar slot 2 or slot 3
stand near a safe gap or bridge arena<\/p>\n\n\n\n