Upload PPO Tetris-v5 trained agent
Browse files- Tetris-v5.zip +3 -0
- Tetris-v5/_stable_baselines3_version +1 -0
- Tetris-v5/data +0 -0
- Tetris-v5/policy.optimizer.pth +3 -0
- Tetris-v5/policy.pth +3 -0
- Tetris-v5/pytorch_variables.pth +3 -0
- Tetris-v5/system_info.txt +9 -0
- config.json +0 -0
- replay.mp4 +0 -0
- results.json +1 -1
Tetris-v5.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9165451360ad6a1734bf67ece408f29709d10a46b9aba9c3665d0f13f2c1a5f9
|
3 |
+
size 157654755
|
Tetris-v5/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
Tetris-v5/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Tetris-v5/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08dbd6a17511b9a3472d115f8ca2c5b851a55e55a4f312ca98eb2ff4c3f1aba3
|
3 |
+
size 103299882
|
Tetris-v5/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc8b7cd59ee7f3b4bba42b09c79e1043f76800537cfa9078d88815cff4588e7d
|
3 |
+
size 51649522
|
Tetris-v5/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
Tetris-v5/system_info.txt
ADDED
@@ -0,0 +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: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.2.1+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.26.2
|
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": 0.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-
|
|
|
1 |
+
{"mean_reward": 0.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-05T07:05:25.628659"}
|