Hugging Face's logo

qgallouedec
/
a2c-BeamRiderNoFrameskip-v4-2873397222

Reinforcement Learning
stable-baselines3
BeamRiderNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Quentin Gallouédec commited on
Commit
ce976df
·
1 Parent(s): 0123631

Initial commit

Browse files
Files changed (8) hide show
  1. README.md +1 -1
  2. a2c-BeamRiderNoFrameskip-v4.zip +2 -2
  3. a2c-BeamRiderNoFrameskip-v4/data +0 -0
  4. a2c-BeamRiderNoFrameskip-v4/policy.optimizer.pth +1 -1
  5. a2c-BeamRiderNoFrameskip-v4/policy.pth +1 -1
  6. replay.mp4 +2 -2
  7. results.json +1 -1
  8. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: BeamRiderNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 330.00 +/- 108.23
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: BeamRiderNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 404.80 +/- 153.43
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-BeamRiderNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:802ddce9ce3d47eb19d4d0468273ce0dc8e87761eb1e924bba828febbae61b77
3
- size 13693514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531f6a84f5026f77169213b3fdd76426893fa41d20066650c2b91ab48cf47fb0
3
+ size 13693515
a2c-BeamRiderNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
a2c-BeamRiderNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b436bcbcfb627c606ac134a540ee285d068006ce56cab319decb7f23c33d9ed5
3
  size 6760385
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364c2dd18b8c01a28b185b42faa3ca01b082c003359a39751a7108e287297ed4
3
  size 6760385
a2c-BeamRiderNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62b5f18cff361a66b51bd2f464d5db9d94ea1267ae6f97ad86681035f9dc4456
3
  size 6763969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc5e96104ed021eb4b30caa1bd2cfb4d1583f01dce65fc9a50d91676041e2bf
3
  size 6763969
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f191546af9ccf7a6db1fe02620a6d205f668e09c944e7cd20ae2578a528bd6
3
- size 331152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f982f8fda162179070aff54223e0f6dc54cbf9be79427d595a725430ac53c08
3
+ size 342786
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 330.0, "std_reward": 108.22569011098982, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:32:00.181349"}
 
1
+ {"mean_reward": 404.8, "std_reward": 153.4332428126317, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:44:05.186573"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f35712a80a303291f6554151bbc4b08b1ea1e1fc3ae46f4d6ae1290c901f411
3
- size 2896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0f1f030198afb07e8b5acb95d296c5c35627271aafaadf98fe07c59db74da3
3
+ size 2893