SirStone
db99153f65
computeRoundReward used cumulative totalScore/50 — unbounded in long battles (vLoss 353 at round 3160 → 25745 by 3871 in the 5841-round attempt). Cap the score term at 400 before /50: bonus ∈ [0,8], so the critic's value scale stays stable regardless of battle length and across battle boundaries. Reverts the 60-round battle chunking (186e005/da2f825): one battle per campaign for the whole remaining budget; keeps the crash-restart loop, the mid-battle freeze guard and the end-of-battle counter completeness check. Cert (5211, single 60-round battle): 59/60 wins (sole loss = cold-start round 1, score 61), vLoss avg 36.1 / max 148.5, gNorm max 596, zero NaN, zero restarts, counter check passed. Weights persist to round 5211.
99 lines
3.8 KiB
Bash
Executable File
99 lines
3.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Training runner: compile PPO_Bot, then loop the Java battle runner with crash recovery.
|
|
#
|
|
# Usage:
|
|
# ./run.sh [opponent] [rounds]
|
|
#
|
|
# Arguments (also settable via env vars):
|
|
# opponent — bot name under SAMPLE_BOTS_DIR (default: Target)
|
|
# rounds — total rounds to run (default: 100)
|
|
#
|
|
# Env vars:
|
|
# TANK_ROYALE_JAR — path to robocode-tankroyale-runner.jar
|
|
# SAMPLE_BOTS_DIR — path to sample bots archive
|
|
# PPOB_LOG_FILE — JSON lines log file (default: training_log.jsonl in repo root)
|
|
# PPOB_LR, PPOB_CLIP_EPSILON, PPOB_ENTROPY_COEFF, PPOB_VALUE_LOSS_COEFF,
|
|
# PPOB_MAX_GRAD_NORM, PPOB_GAMMA, PPOB_LAM, PPOB_EPOCHS, PPOB_MINI_BATCH_SIZE
|
|
# — hyperparameters (all optional, PPO_Bot uses sensible defaults)
|
|
set -uo pipefail
|
|
|
|
ENV_FILE="$(cd "$(dirname "$0")" && pwd)/training.env"
|
|
[ -f "$ENV_FILE" ] && set -a && . "$ENV_FILE" && set +a
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
|
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
|
|
|
|
OPPONENT="${1:-${TRAINING_OPPONENT:-Target}}"
|
|
TOTAL_ROUNDS="${2:-${TRAINING_ROUNDS:-100}}"
|
|
|
|
JAR="${TANK_ROYALE_JAR:-/home/davide/Projects/tank-royale/runner/examples/lib/robocode-tankroyale-runner.jar}"
|
|
PPO_BOT_SRC="$REPO_ROOT/PPO_Bot"
|
|
|
|
export PPO_BOT_DIR="$PPO_BOT_SRC"
|
|
export SAMPLE_BOTS_DIR="${SAMPLE_BOTS_DIR:-/home/davide/Projects/tank-royale/sample-bots/java/build/archive}"
|
|
export PPOB_LOG_FILE="${PPOB_LOG_FILE:-$REPO_ROOT/training_log.jsonl}"
|
|
|
|
echo "=== Training runner ==="
|
|
echo "Opponent: $OPPONENT"
|
|
echo "Total rounds: $TOTAL_ROUNDS"
|
|
echo "Log file: $PPOB_LOG_FILE"
|
|
echo ""
|
|
|
|
# ── 1. Compile PPO_Bot ────────────────────────────────────────────────────────
|
|
echo ">>> Compiling PPO_Bot..."
|
|
(cd "$PPO_BOT_SRC" && nimble build -d:release)
|
|
echo ">>> PPO_Bot compiled."
|
|
|
|
# ── 2. Compile RunTraining.java ───────────────────────────────────────────────
|
|
cd "$SCRIPT_DIR"
|
|
echo ">>> Compiling RunTraining.java..."
|
|
javac -cp "$JAR" RunTraining.java
|
|
echo ">>> RunTraining compiled."
|
|
|
|
# ── 3. Run with crash-restart loop ───────────────────────────────────────────
|
|
# We pass total rounds to the Java runner. On crash, restart from where we left
|
|
# off by reading the round counter PPO_Bot persists to weights/round_counter.txt.
|
|
# ponytail: simple restart from persisted counter; no partial-round recovery needed
|
|
|
|
ROUND_COUNTER_FILE="$PPO_BOT_SRC/weights/round_counter.txt"
|
|
|
|
remaining_rounds() {
|
|
local done=0
|
|
if [ -f "$ROUND_COUNTER_FILE" ]; then
|
|
done=$(cat "$ROUND_COUNTER_FILE" 2>/dev/null || echo 0)
|
|
fi
|
|
echo $(( TOTAL_ROUNDS - done ))
|
|
}
|
|
|
|
attempts=0
|
|
while true; do
|
|
remaining=$(remaining_rounds)
|
|
if [ "$remaining" -le 0 ]; then
|
|
echo ">>> All $TOTAL_ROUNDS rounds complete."
|
|
break
|
|
fi
|
|
|
|
attempts=$(( attempts + 1 ))
|
|
if [ "$attempts" -gt 1 ]; then
|
|
echo ">>> Restart #$attempts — $remaining rounds remaining..."
|
|
sleep 2
|
|
fi
|
|
|
|
# One battle for the whole remaining budget: round-end reward is a bounded
|
|
# terminal bonus (computeRoundReward caps totalScore at 400), so long battles
|
|
# keep the critic's value scale stable — no per-battle chunking needed.
|
|
echo ">>> Running $remaining rounds (opponent: $OPPONENT)..."
|
|
java -cp ".:$JAR" RunTraining "$OPPONENT" "$remaining" || {
|
|
exit_code=$?
|
|
echo ">>> Java runner exited with code $exit_code — checking if done..."
|
|
remaining=$(remaining_rounds)
|
|
if [ "$remaining" -le 0 ]; then
|
|
echo ">>> All rounds complete despite non-zero exit."
|
|
break
|
|
fi
|
|
echo ">>> Crash detected ($remaining rounds remain). Restarting..."
|
|
}
|
|
done
|
|
|
|
echo ">>> Training done. Log at $PPOB_LOG_FILE"
|