Hugging Face's logo

zap-thamm
/
PPO-Taxi-v3

Reinforcement Learning
Taxi-v3
rl-framework
Eval Results
Model card Files Community
1
zap-thamm commited on
Commit
5e09b0a
•
1 Parent(s): 5fc2da2

Upload of a new agent trained with PPO on Taxi-v3

Browse files
Files changed (4) hide show
  1. algorithm.zip +2 -2
  2. replay.mp4 +0 -0
  3. results.json +1 -1
  4. system.json +1 -1
algorithm.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfd6b8e631560f246dc925f811f4ab1923c33bf80cbb81b41fe5532b0ed07a5a
3
- size 906205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad1db02c0e29425c51e182a697c2e911f6b06b40604c95f9e28f14574767929
3
+ size 905866
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Taxi-v3", "mean_reward": -200.0, "n_eval_episodes": 50, "eval_datetime": "2023-12-08T10:00:24.282221"}
 
1
+ {"env_id": "Taxi-v3", "mean_reward": -200.0, "n_eval_episodes": 50, "eval_datetime": "2023-12-12T14:31:33.348795"}
system.json CHANGED
@@ -1 +1 @@
1
- {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.9.13", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.1+cpu", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}
 
1
+ {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.10.8", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.1+cpu", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}