# TRAINING_OPPONENT=Fire TRAINING_ROUNDS=30000 PPOB_LOG_FILE=/home/davide/Projects/SirRoboGarage/tools/training_runner/logs/fire_training.jsonl PPOB_LR=1e-4 PPOB_UPDATE_INTERVAL=10 PPOB_CLIP_EPSILON=0.2 PPOB_ENTROPY_COEFF=0.001 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_LOG_STD_CEILING=0.0 PPOB_INITIAL_LOG_STD=-0.5 # PPOB_EVAL_ONLY=1 → freeze training (pure evaluation)