SirStone
82eeb53e5c
- generalist_train.sh: CHUNK_SIZE 60→20 for faster opponent cycling - generalist_train.sh: EVAL_ROUNDS 30→50 for more reliable eval - training.env: TRAINING_ROUNDS→30000, removed hardcoded opponent - warm_start.py: TARGET_DIM=57 (already committed, ensure latest)
17 lines
429 B
Bash
17 lines
429 B
Bash
# TRAINING_OPPONENT=Fire
|
|
TRAINING_ROUNDS=30000
|
|
PPOB_LOG_FILE=/home/davide/Projects/SirRoboGarage/tools/training_runner/logs/fire_training.jsonl
|
|
PPOB_LR=0.0003
|
|
PPOB_CLIP_EPSILON=0.2
|
|
PPOB_ENTROPY_COEFF=0.01
|
|
PPOB_VALUE_LOSS_COEFF=0.5
|
|
PPOB_MAX_GRAD_NORM=0.5
|
|
PPOB_GAMMA=0.99
|
|
PPOB_LAM=0.95
|
|
PPOB_EPOCHS=4
|
|
PPOB_MINI_BATCH_SIZE=64
|
|
PPOB_LOG_STD_FLOOR=-3.0
|
|
PPOB_INITIAL_LOG_STD=0.0
|
|
|
|
# PPOB_EVAL_ONLY=1 → freeze training (pure evaluation)
|