feat(SAC_LSTM_Bot): training harness (#49)

sac_train.sh orchestrates chunked self-play via tools/training_runner/
RunTraining.java: weighted opponent sampling per chunk, deterministic
eval (SACLSTM_EVAL_MODE=1) every N chunks with win-rate tracking, best
checkpoint (weights/sac_best.zip) by eval score, crash-restart loop on
the runner's liveness detection.

Supporting changes:
- integration.nim: opponentKey() keys the NewBattle buffer-clear rule on
  getBotName(id) with numeric-id fallback (#49 Q14 follow-up);
  bumpRoundCounter() emits the per-round liveness signal.
- SAC_LSTM_Bot.nim: onRoundEnded -> bumpRoundCounter().
- RunTraining.java: BOT_NAME env parameterizes result matching
  (default PPO_Bot, unchanged behavior for PPO).
- Launch packaging: root SAC_LSTM_Bot.json + .sh for the booter;
  src json name aligned to 'SAC_LSTM_Bot' so self-reported identity
  matches the booted identity (mismatch = runner connect timeout).

This commit is contained in:

Davide Cappellini

2026-08-21 21:51:27 +02:00

parent 7104645f5d

commit df256b4d3e

8 changed files with 222 additions and 21 deletions

									
										SAC_LSTM_Bot/SAC_LSTM_Bot.sh
									
Executable

		+4
		
												View File
												
				@@ -0,0 +1,4 @@

				#!/bin/sh

				# Launch config for tools/training_runner/RunTraining.java (#49): the runner

				# executes <json-basename>.sh inside the bot dir (sample-bots convention).

				exec "$(dirname "$0")/SAC_LSTM_Bot"