Hugging Face's logo

nsanghi
/
a2c-Atari-Pong

Reinforcement Learning
stable-baselines3
PongNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
nsanghi commited on
Commit
38daf50
•
1 Parent(s): ece7f6c

Push to Hub

Browse files
Files changed (9) hide show
  1. A2C-Atari-Pong.zip +2 -2
  2. A2C-Atari-Pong/data +0 -0
  3. A2C-Atari-Pong/policy.optimizer.pth +1 -1
  4. A2C-Atari-Pong/policy.pth +1 -1
  5. A2C-Atari-Pong/system_info.txt +3 -3
  6. README.md +1 -1
  7. config.json +0 -0
  8. replay.mp4 +0 -0
  9. results.json +1 -1
A2C-Atari-Pong.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:516af8d0bc107a74d94b9f8600ebd66a257d6438c379cd1cd5d7e9cf162d9d95
3
- size 13827400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f8c951b3b5643b1e454377ad877a3af2f143441122a6b9fa40de5811303491
3
+ size 13827419
A2C-Atari-Pong/data CHANGED
The diff for this file is too large to render. See raw diff
 
A2C-Atari-Pong/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9cdc478013e89a32772df1fc0b10d00f423c8d6d6159b607fc50b379f89aa23
3
  size 6754674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9f4d43304ce2ffa682d7f1feb663c903855142d34d433878bdd32457f7af6b
3
  size 6754674
A2C-Atari-Pong/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d596a2f248955e7fc8608b5f4593bdbf2e6efda3723016c340be18bd01e3da3
3
  size 6757874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab431deef062e75293b53d874eb164173f1f0c342ebed3dfabcd849a10e61159
3
  size 6757874
A2C-Atari-Pong/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Oct 5 21:02:42 UTC 2023
2
  - Python: 3.9.18
3
  - Stable-Baselines3: 2.1.0
4
- - PyTorch: 2.1.0+cpu
5
  - GPU Enabled: False
6
- - Numpy: 1.26.1
7
  - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
 
1
+ - OS: Linux-6.2.0-1019-azure-x86_64-with-glibc2.36 # 19~22.04.1-Ubuntu SMP Wed Jan 10 22:57:03 UTC 2024
2
  - Python: 3.9.18
3
  - Stable-Baselines3: 2.1.0
4
+ - PyTorch: 2.2.1+cpu
5
  - GPU Enabled: False
6
+ - Numpy: 1.26.4
7
  - Cloudpickle: 3.0.0
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: -20.00 +/- 1.18
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: -20.50 +/- 0.67
20
  name: mean_reward
21
  verified: false
22
  ---
config.json CHANGED
The diff for this file is too large to render. See raw diff
 
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -20.0, "std_reward": 1.1832159566199232, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T12:49:38.381269"}
 
1
+ {"mean_reward": -20.5, "std_reward": 0.6708203932499369, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T09:49:06.066938"}