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

chore(exp22): update wedgefix run log — training stopped for strategy rethink 

Run stopped at ~34k steps. ep_len_mean frozen at 118 due to MAX_EPISODE_SECONDS=18
cap. Barriers identified as zero-thickness MeshColliders (physics tunneling root cause).
Clean-slate rebuild planned: BoxCollider barriers + CCD on car + simplified reward.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Paul Huliganga 2026-05-05 15:36:18 -04:00
parent 138c65270f
commit c5c4ca658e
1 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
agent/models/exp22-generated-pair-warm-v6/run_2026-05-05_142620_wedgefix.log
View File

@ -119,3 +119,25 @@ INFO:gym_donkeycar.envs.donkey_sim:sim started!
| time_elapsed | 180 |
| total_timesteps | 30720 |
---------------------------------
-----------------------------------------
| rollout/ | |
| ep_len_mean | 118 |
| ep_rew_mean | 102 |
| time/ | |
| fps | 17 |
| iterations | 2 |
| time_elapsed | 465 |
| total_timesteps | 34816 |
| train/ | |
| approx_kl | 0.024647033 |
| clip_fraction | 0.208 |
| clip_range | 0.2 |
| entropy_loss | -2.71 |
| explained_variance | -0.688 |
| learning_rate | 0.000225 |
| loss | -0.00317 |
| n_updates | 110 |
| policy_gradient_loss | -0.0268 |
| std | 0.921 |
| value_loss | 0.228 |
-----------------------------------------