Upload DQN PongNoFrameskip-v4 trained agent
Browse files- config.json +0 -0
- dqn-PongNoFrameskip-v4.zip +2 -2
- dqn-PongNoFrameskip-v4/data +0 -0
- dqn-PongNoFrameskip-v4/policy.optimizer.pth +1 -1
- dqn-PongNoFrameskip-v4/policy.pth +2 -2
- dqn-PongNoFrameskip-v4/system_info.txt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
dqn-PongNoFrameskip-v4.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbdc891a6a4f8e023115e326ecc3c507921afd7e1170005f2fa181fb7ee48554
|
3 |
+
size 93740643
|
dqn-PongNoFrameskip-v4/data
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
dqn-PongNoFrameskip-v4/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
|
3 |
size 1120
|
dqn-PongNoFrameskip-v4/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:446753c2f65d1f5fc190c8d14cca7304fcfcf9c5c2892f212e001c9c46c2ab99
|
3 |
+
size 92918426
|
dqn-PongNoFrameskip-v4/system_info.txt
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.2.0a9
|
4 |
- PyTorch: 2.1.0+cu118
|
5 |
-
- GPU Enabled:
|
6 |
- Numpy: 1.23.5
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.29.1
|
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.2.0a9
|
4 |
- PyTorch: 2.1.0+cu118
|
5 |
+
- GPU Enabled: False
|
6 |
- Numpy: 1.23.5
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.29.1
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -21.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-02T16:
|
|
|
1 |
+
{"mean_reward": -21.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-02T16:23:43.651127"}
|