paulh
/
donkeycar-rl-autoresearch
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: exp11d remove progress_patience — grass fix only per ADR-020

This commit is contained in:
Paul Huliganga 2026-04-19 16:18:17 -04:00
parent e95c33c1bf
commit dc563e2b6c
1 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
agent/experiments/exp11d_parallel_v61.py
View File

@ -43,7 +43,6 @@ def make_env(track_id, port):
env = SpeedRewardWrapper(env, env = SpeedRewardWrapper(env,
max_cte_terminate=4.0, # terminate if CTE > 4m for 20 steps (grass fix) max_cte_terminate=4.0, # terminate if CTE > 4m for 20 steps (grass fix)
cte_patience=20, cte_patience=20,
progress_patience=60, # terminate if no node advance for 60 steps (rollback fix)
) )
return env return env
return _init return _init
@ -53,9 +52,8 @@ log('Exp 11d: Parallel DummyVecEnv, v6.1 reward, 180k steps')
log(f' Sim 1: {HOST}:9091 → generated_track') log(f' Sim 1: {HOST}:9091 → generated_track')
log(f' Sim 2: {HOST}:9093 → mountain_track') log(f' Sim 2: {HOST}:9093 → mountain_track')
log(f' throttle_min={THROTTLE_MIN}, lr={LR}, total={TOTAL_STEPS:,}') log(f' throttle_min={THROTTLE_MIN}, lr={LR}, total={TOTAL_STEPS:,}')
log(f' Reward v6.1: speed×CTE + efficiency gate + grass/rollback terminators') log(f' Reward v6.1: speed×CTE + efficiency gate + grass exploit terminator')
log(f' max_cte_terminate=4.0, cte_patience=20 (grass fix)') log(f' max_cte_terminate=4.0, cte_patience=20 (grass fix only)')
log(f' progress_patience=60 (mountain rollback fix)')
log(f' Stuck: 40 steps') log(f' Stuck: 40 steps')
log('='*60) log('='*60)
@ -141,8 +139,7 @@ for track_id, track_name in EVAL_TRACKS:
raw = gym.make(track_id, conf={'host': HOST, 'port': EVAL_PORT}) raw = gym.make(track_id, conf={'host': HOST, 'port': EVAL_PORT})
ei = ThrottleClampWrapper(raw, throttle_min=THROTTLE_MIN) ei = ThrottleClampWrapper(raw, throttle_min=THROTTLE_MIN)
ei = StuckTerminationWrapper(ei, stuck_steps=40, min_displacement=0.5) ei = StuckTerminationWrapper(ei, stuck_steps=40, min_displacement=0.5)
ei = SpeedRewardWrapper(ei, max_cte_terminate=4.0, cte_patience=20, ei = SpeedRewardWrapper(ei, max_cte_terminate=4.0, cte_patience=20)
progress_patience=60)
ev = VecTransposeImage(DummyVecEnv([lambda e=ei: e])) ev = VecTransposeImage(DummyVecEnv([lambda e=ei: e]))
m = PPO.load(best_model_path, env=ev, device='cpu') m = PPO.load(best_model_path, env=ev, device='cpu')