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

fix: save_dir not in scope inside train_multitrack — crashed every trial 

Checkpoint code added save_dir inside train_multitrack() but save_dir
is defined in main(). Every trial since the checkpoint fix was added
crashed with 'name save_dir is not defined' after the first segment,
producing rc=101 and no GP data.

Fix: add save_dir=None parameter to train_multitrack() and pass it
from the main() call site.

This explains why Trials 6-10 in the current run all produced None
results despite appearing to train normally for the first segment.

Agent: pi
Tests: 102 passed
Tests-Added: 0
TypeScript: N/A
This commit is contained in:
Paul Huliganga 2026-04-15 22:47:29 -04:00
parent ff8bdd8b8a
commit b00f63dfbc
5 changed files with 46 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
agent/multitrack_runner.py
View File

@ -290,7 +290,8 @@ def create_or_load_model(env, learning_rate, warm_start_path=None, seed=None):
# ---- Training loop ---- # ---- Training loop ----
def train_multitrack(model, first_env, total_timesteps, steps_per_switch): def train_multitrack(model, first_env, total_timesteps, steps_per_switch,
save_dir=None):
""" """
Train PPO across training tracks by round-robin switching every steps_per_switch steps. Train PPO across training tracks by round-robin switching every steps_per_switch steps.
@ -542,6 +543,7 @@ def main():
model, env, model, env,
total_timesteps=args.total_timesteps, total_timesteps=args.total_timesteps,
steps_per_switch=args.steps_per_switch, steps_per_switch=args.steps_per_switch,
save_dir=save_dir,
) )
except Exception as e: except Exception as e:
log(f'[W3 Runner] ❌ Training failed: {e}') log(f'[W3 Runner] ❌ Training failed: {e}')

13
agent/outerloop-results/autoresearch_phase2_log.txt
View File

@ -697,3 +697,16 @@
[2026-04-15 22:26:26] [Champion] 🏆 NEW BEST! Trial 3: mean_reward=90.0000 params={'r': 90} [2026-04-15 22:26:26] [Champion] 🏆 NEW BEST! Trial 3: mean_reward=90.0000 params={'r': 90}
[2026-04-15 22:26:26] [Champion] 🏆 NEW BEST! Trial 5: mean_reward=75.0000 params={'n_steer': 8} [2026-04-15 22:26:26] [Champion] 🏆 NEW BEST! Trial 5: mean_reward=75.0000 params={'n_steer': 8}
[2026-04-15 22:26:26] [AutoResearch] Only 1 results — using random proposal. [2026-04-15 22:26:26] [AutoResearch] Only 1 results — using random proposal.
[2026-04-15 22:47:03] [AutoResearch] GP UCB top-5 candidates:
[2026-04-15 22:47:03] UCB=2.3107 mu=0.3981 sigma=0.9563 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.001405531880392808, 'timesteps': 26173}
[2026-04-15 22:47:03] UCB=2.3049 mu=0.8602 sigma=0.7224 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.001793493447174312, 'timesteps': 19198}
[2026-04-15 22:47:03] UCB=2.2813 mu=0.4904 sigma=0.8954 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0011616192816742616, 'timesteps': 13887}
[2026-04-15 22:47:03] UCB=2.2767 mu=0.5194 sigma=0.8787 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0011646447444663046, 'timesteps': 21199}
[2026-04-15 22:47:03] UCB=2.2525 mu=0.6254 sigma=0.8136 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0010196345864901517, 'timesteps': 22035}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=50.0000 params={'n_steer': 5}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=80.0000 params={'n_steer': 7}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 0: mean_reward=50.0000 params={'r': 50}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=80.0000 params={'r': 80}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 3: mean_reward=90.0000 params={'r': 90}
[2026-04-15 22:47:03] [Champion] 🏆 NEW BEST! Trial 5: mean_reward=75.0000 params={'n_steer': 8}
[2026-04-15 22:47:03] [AutoResearch] Only 1 results — using random proposal.

5
agent/outerloop-results/autoresearch_phase3_log.txt
View File

@ -380,3 +380,8 @@
[2026-04-15 22:26:39] [Wave3] Only 0 results — using random proposal. [2026-04-15 22:26:39] [Wave3] Only 0 results — using random proposal.
[2026-04-15 22:26:39] [Champion] 🏆 NEW BEST! Trial 3: score=1500.00 (mini_monaco=1500.0) params={'learning_rate': 0.0002, 'steps_per_switch': 8000, 'total_timesteps': 150000} [2026-04-15 22:26:39] [Champion] 🏆 NEW BEST! Trial 3: score=1500.00 (mini_monaco=1500.0) params={'learning_rate': 0.0002, 'steps_per_switch': 8000, 'total_timesteps': 150000}
[2026-04-15 22:26:39] [Champion] 🏆 NEW BEST! Trial 1: score=2000.00 (mini_monaco=2000.0) params={} [2026-04-15 22:26:39] [Champion] 🏆 NEW BEST! Trial 1: score=2000.00 (mini_monaco=2000.0) params={}
[2026-04-15 22:47:16] [Wave3] Seed trial 1/2: using hardcoded params.
[2026-04-15 22:47:16] [Wave3] Seed trial 2/2: using hardcoded params.
[2026-04-15 22:47:16] [Wave3] Only 0 results — using random proposal.
[2026-04-15 22:47:16] [Champion] 🏆 NEW BEST! Trial 3: score=1500.00 (mini_monaco=1500.0) params={'learning_rate': 0.0002, 'steps_per_switch': 8000, 'total_timesteps': 150000}
[2026-04-15 22:47:16] [Champion] 🏆 NEW BEST! Trial 1: score=2000.00 (mini_monaco=2000.0) params={}

24
agent/outerloop-results/autoresearch_phase4_log.txt
View File

@ -364,3 +364,27 @@
[2026-04-15 22:26:54] [Wave4] Proposed params: {'learning_rate': 0.0009434282949002715, 'steps_per_switch': 14966, 'total_timesteps': 83094} [2026-04-15 22:26:54] [Wave4] Proposed params: {'learning_rate': 0.0009434282949002715, 'steps_per_switch': 14966, 'total_timesteps': 83094}
[2026-04-15 22:26:56] [Wave4] Launching trial 6: {'learning_rate': 0.0009434282949002715, 'steps_per_switch': 14966, 'total_timesteps': 83094} [2026-04-15 22:26:56] [Wave4] Launching trial 6: {'learning_rate': 0.0009434282949002715, 'steps_per_switch': 14966, 'total_timesteps': 83094}
[2026-04-15 22:26:56] [Wave4] Command: python3 /home/paulh/projects/donkeycar-rl-autoresearch/agent/multitrack_runner.py --total-timesteps 83094 --steps-per-switch 14966 --learning-rate 0.0009434282949002715 --eval-episodes 3 --save-dir /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0006 [2026-04-15 22:26:56] [Wave4] Command: python3 /home/paulh/projects/donkeycar-rl-autoresearch/agent/multitrack_runner.py --total-timesteps 83094 --steps-per-switch 14966 --learning-rate 0.0009434282949002715 --eval-episodes 3 --save-dir /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0006
[2026-04-15 22:38:49] [Wave4] Trial 6 finished in 712.6s, rc=101
[2026-04-15 22:38:49] [Wave4] Parsed: combined=None mini_monaco=None
[2026-04-15 22:38:49] [Wave4] ⚠️ No test score parsed — defaulting to 0.0
[2026-04-15 22:38:49] [Wave4] combined_test_score=0 — excluded from GP (crash/timeout).
[2026-04-15 22:38:49] [Wave4] ===== Trial 6 Summary =====
[2026-04-15 22:38:49] GP data points : 5
[2026-04-15 22:38:49] Wave4 Champion: trial=3 score=1943.10 params={'learning_rate': 0.0006852550685205609, 'steps_per_switch': 17499, 'total_timesteps': 157743}
[2026-04-15 22:38:49] Top 5:
[2026-04-15 22:38:49] score=1943.10 params={'learning_rate': 0.0006852550685205609, 'steps_per_switch': 17499, 'total_timesteps': 90000}
[2026-04-15 22:38:49] score=176.67 params={'learning_rate': 0.0016223486895735558, 'steps_per_switch': 5524, 'total_timesteps': 79532}
[2026-04-15 22:38:49] score=93.39 params={'learning_rate': 0.001, 'steps_per_switch': 6000, 'total_timesteps': 80000}
[2026-04-15 22:38:49] score=42.30 params={'learning_rate': 0.0003, 'steps_per_switch': 6000, 'total_timesteps': 80000}
[2026-04-15 22:38:49] score=31.73 params={'learning_rate': 0.0007517877668650138, 'steps_per_switch': 9368, 'total_timesteps': 104878}
[2026-04-15 22:38:51]
[Wave4] ========== Trial 7/25 ==========
[2026-04-15 22:38:51] [Wave4] GP UCB top-5 proposals:
[2026-04-15 22:38:51] UCB=2.8131 mu=1.4171 σ=0.6980 params={'learning_rate': 0.0004346662414818233, 'steps_per_switch': 14860, 'total_timesteps': 83818}
[2026-04-15 22:38:51] UCB=2.7278 mu=1.2363 σ=0.7458 params={'learning_rate': 0.00020210801580883826, 'steps_per_switch': 14145, 'total_timesteps': 88060}
[2026-04-15 22:38:51] UCB=2.7159 mu=1.0082 σ=0.8538 params={'learning_rate': 0.00012352374581522935, 'steps_per_switch': 14555, 'total_timesteps': 84897}
[2026-04-15 22:38:51] UCB=2.6982 mu=1.4815 σ=0.6084 params={'learning_rate': 0.0010645009917759616, 'steps_per_switch': 14511, 'total_timesteps': 89107}
[2026-04-15 22:38:51] UCB=2.6948 mu=1.1351 σ=0.7798 params={'learning_rate': 0.0012021332143154963, 'steps_per_switch': 14377, 'total_timesteps': 87121}
[2026-04-15 22:38:51] [Wave4] Proposed params: {'learning_rate': 0.0004346662414818233, 'steps_per_switch': 14860, 'total_timesteps': 83818}
[2026-04-15 22:38:53] [Wave4] Launching trial 7: {'learning_rate': 0.0004346662414818233, 'steps_per_switch': 14860, 'total_timesteps': 83818}
[2026-04-15 22:38:53] [Wave4] Command: python3 /home/paulh/projects/donkeycar-rl-autoresearch/agent/multitrack_runner.py --total-timesteps 83818 --steps-per-switch 14860 --learning-rate 0.0004346662414818233 --eval-episodes 3 --save-dir /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0007

1
agent/outerloop-results/autoresearch_results_phase4.jsonl
View File

@ -3,3 +3,4 @@
{"trial": 5, "timestamp": "2026-04-15T17:08:50.252022", "params": {"learning_rate": 0.0007517877668650138, "steps_per_switch": 9368, "total_timesteps": 104878}, "combined_test_score": 31.73, "mini_monaco_reward": 31.73, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0005/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 5348.823204040527} {"trial": 5, "timestamp": "2026-04-15T17:08:50.252022", "params": {"learning_rate": 0.0007517877668650138, "steps_per_switch": 9368, "total_timesteps": 104878}, "combined_test_score": 31.73, "mini_monaco_reward": 31.73, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0005/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 5348.823204040527}
{"trial": 6, "timestamp": "2026-04-15T18:19:30.998330", "params": {"learning_rate": 0.0016223486895735558, "steps_per_switch": 5524, "total_timesteps": 79532}, "combined_test_score": 176.6721, "mini_monaco_reward": 176.6721, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0006/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 4235.310993909836} {"trial": 6, "timestamp": "2026-04-15T18:19:30.998330", "params": {"learning_rate": 0.0016223486895735558, "steps_per_switch": 5524, "total_timesteps": 79532}, "combined_test_score": 176.6721, "mini_monaco_reward": 176.6721, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0006/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 4235.310993909836}
{"trial": 0, "timestamp": "2026-04-15T03:15:46", "params": {"learning_rate": 0.0006852550685205609, "steps_per_switch": 17499, "total_timesteps": 90000}, "combined_test_score": 1943.1, "mini_monaco_reward": 1943.1, "model_path": "agent/models/wave4-trial-0003/model.zip", "champion": true, "run_status": "ok_pre_patch", "elapsed_sec": 5766.0, "note": "Pre-exploit-patch overnight run. Model on disk. steps_per_switch capped for GP."} {"trial": 0, "timestamp": "2026-04-15T03:15:46", "params": {"learning_rate": 0.0006852550685205609, "steps_per_switch": 17499, "total_timesteps": 90000}, "combined_test_score": 1943.1, "mini_monaco_reward": 1943.1, "model_path": "agent/models/wave4-trial-0003/model.zip", "champion": true, "run_status": "ok_pre_patch", "elapsed_sec": 5766.0, "note": "Pre-exploit-patch overnight run. Model on disk. steps_per_switch capped for GP."}
{"trial": 6, "timestamp": "2026-04-15T22:38:49.383770", "params": {"learning_rate": 0.0009434282949002715, "steps_per_switch": 14966, "total_timesteps": 83094}, "combined_test_score": 0.0, "mini_monaco_reward": 0.0, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0006/model.zip", "champion": false, "run_status": "error_rc101", "elapsed_sec": 712.563179731369}