Gaming RL is the generic first-person gaming reinforcement-learning subsystem.<\/p>\n\n\n\n
It is separate from Minecraft DQN, but it follows the same structure: observe<\/p>\n\n\n\n
state, choose actions, record transitions, train\/evaluate policies, and only<\/p>\n\n\n\n
actuate when the selected mode permits it.<\/p>\n\n\n\n
Use this only in local\/private environments where automation is allowed.<\/p>\n\n\n\n
RL hub:<\/strong> ReinforcementLearning.md (ReinforcementLearning.md) \u00b7 MathNN:<\/p>\n\n\n\n rl net enable gaming_fps \/ rl net mode gaming_fps actor-critic \u2014 see<\/p>\n\n\n\n MathNN.md (MathNN.md).<\/p>\n\n\n\n For the full FPS state\/action reference, see docs\/GamingRLFPS.md. For Source,<\/p>\n\n\n\n Quake, Garry’s Mod, and Civilization bridge setup, see<\/p>\n\n\n\n docs\/GameModBridges.md.<\/p>\n\n\n\n [text] Start in dry-run:<\/p>\n\n\n\n [text] Game mod bridge smoke test:<\/p>\n\n\n\n [text] [text] Commands:<\/p>\n\n\n\n [text] [text] skill use forces one action and is useful for checking input routing.<\/p>\n\n\n\n [text] Adapters are responsible for filling FPSPerception: target location, HUD<\/p>\n\n\n\n values, menu\/death state, hit markers, audio threat, minimap threat, objective<\/p>\n\n\n\n distance, and movement context.<\/p>\n\n\n\n source_mod, quake_mod, and garrys_mod provide server-side<\/p>\n\n\n\n health\/damage\/death telemetry. Use them together with client-side<\/p>\n\n\n\n screen\/HUD\/audio perception when training aim or navigation policies.<\/p>\n\n\n\n civilization_mod feeds turn-state observations into GamingStrategyRL and<\/p>\n\n\n\n returns high-level strategy recommendations such as prioritize_science,<\/p>\n\n\n\n raise_military, scout, and settle_city.<\/p>\n\n\n\n [text] Use dry-run on until observations and action selection are correct. `input<\/p>\n\n\n\n hold controls timed key holds for smoother movement. input mouse` limits mouse<\/p>\n\n\n\n movement per tick.<\/p>\n\n\n\n [text] Recommended phase order:<\/p>\n\n\n\n [text] [text] Replay training imports transition logs. Behavior cloning trains from imitation<\/p>\n\n\n\n examples managed by GamingSimulation.<\/p>\n\n\n\n [text] Default log directory:<\/p>\n\n\n\n [text] Important files:<\/p>\n\n\n\n [text] Agents can call:<\/p>\n\n\n\n [text] Gaming RL is the generic first-person gaming reinforcement-learning subsystem. It is separate from Minecraft DQN, but it follows the same structure: observe state, choose actions, record transitions, train\/evaluate policies, and only actuate when the selected mode permits it. Use this only in local\/private environments where automation is allowed. RL hub: ReinforcementLearning.md (ReinforcementLearning.md) \u00b7 MathNN: rl […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-1989","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/posts\/1989","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/comments?post=1989"}],"version-history":[{"count":1,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/posts\/1989\/revisions"}],"predecessor-version":[{"id":1990,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/posts\/1989\/revisions\/1990"}],"wp:attachment":[{"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/media?parent=1989"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/categories?post=1989"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/macdaddy4sure.ai\/index.php\/wp-json\/wp\/v2\/tags?post=1989"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Modes<\/h2>\n\n\n\n
<\/em>off
assist
bot
train
eval
imitate<\/p>\n\n\n\n
<\/em>gaming rl init
gaming rl adapter set generic_fps
gaming rl dry-run on
gaming rl input hold 120
gaming rl input mouse 32
gaming rl status<\/p>\n\n\n\n
<\/em>gaming rl init
gaming rl dry-run on
gaming mod bridge configure source_mod 0.0.0.0 8767 YOUR_TOKEN true
gaming mod bridge configure quake_mod 0.0.0.0 8768 YOUR_TOKEN true
gaming mod bridge configure garrys_mod 0.0.0.0 8771 YOUR_TOKEN true
gaming mod bridge configure civilization_mod 0.0.0.0 8772 YOUR_TOKEN true
gaming mod bridge status
gaming mod bridge tail source_mod 10<\/p>\n\n\n\nAlgorithms<\/h2>\n\n\n\n
<\/em>heuristic
random
qtable
linear_q
sarsa
reinforce
mlp
dqn
remote
auto<\/p>\n\n\n\n
<\/em>gaming rl algorithm heuristic
gaming rl algorithm qtable
gaming rl algorithm linear_q
gaming rl algorithm dqn
gaming rl algorithm auto
gaming rl epsilon <value>
gaming rl blend <value><\/p>\n\n\n\nCore Commands<\/h2>\n\n\n\n
<\/em>gaming rl status
gaming rl features
gaming rl systems
gaming rl skills
gaming rl skill use <action_id>
gaming rl explain
gaming rl why
gaming rl on
gaming rl assist
gaming rl bot
gaming rl train
gaming rl eval [episodes]
gaming rl off<\/p>\n\n\n\nAdapter And Perception<\/h2>\n\n\n\n
<\/em>gaming rl adapter status
gaming rl adapter set <name>
gaming rl perception <request>
gaming rl bridge spec
gaming mod bridge status
gaming mod bridge start [source_mod|quake_mod|garrys_mod|civilization_mod|all]
gaming mod bridge tail [source_mod|quake_mod|garrys_mod|civilization_mod|all] [count]<\/p>\n\n\n\nInput Safety<\/h2>\n\n\n\n
<\/em>gaming rl dry-run on
gaming rl dry-run off
gaming rl input hold <milliseconds>
gaming rl input mouse <max_pixels_per_tick><\/p>\n\n\n\nCurriculum<\/h2>\n\n\n\n
<\/em>gaming rl curriculum status
gaming rl curriculum start [phase]
gaming rl curriculum next
gaming rl curriculum phase <name><\/p>\n\n\n\n
<\/em>input_smoke
aim_static
aim_tracking
movement_basic
cover_peek
objective_push
offline_replay
eval_gate<\/p>\n\n\n\nReplay And Behavior Cloning<\/h2>\n\n\n\n
<\/em>gaming rl replay summary [path]
gaming rl replay tail
gaming rl replay train [path]
gaming rl bc train [epochs]
gaming rl bc status<\/p>\n\n\n\nRewards And Checkpoints<\/h2>\n\n\n\n
<\/em>gaming rl reward good [note]
gaming rl reward bad [note]
gaming rl reward <number> [note]
gaming rl checkpoint tag <tag>
gaming rl checkpoint list
gaming rl checkpoint rollback <tag>
gaming rl save
gaming rl load
gaming rl save mysql
gaming rl load mysql
gaming rl checkpoint mysql on
gaming rl checkpoint mysql off
gaming rl checkpoint mysql profile <profile><\/p>\n\n\n\nRuntime Files<\/h2>\n\n\n\n
<\/em>D:\/gaming_rl_logs<\/p>\n\n\n\n
<\/em>gaming_rl_checkpoint.txt
transitions.csv
fps_dashboard.json
fps_heatmap.csv
fps_bridge_protocol.json
fps_perception_requests.jsonl
fps_episode_events.jsonl
checkpoint_<tag>.txt<\/p>\n\n\n\nLua Globals<\/h2>\n\n\n\n
<\/em>gaming_rl_status()
gaming_rl_set_mode(mode)
gaming_rl_get_mode()
gaming_rl_set_algorithm(algorithm)
gaming_rl_get_algorithm()
gaming_rl_start_episode()
gaming_rl_end_episode()
gaming_rl_save()
gaming_rl_load()
gaming_rl_save_mysql()
gaming_rl_load_mysql()
gaming_rl_init()
gaming_rl_shutdown()<\/p>\n\n\n\nSafe Operating Pattern<\/h2>\n\n\n\n
\n