pkalkman commited on
Commit
919c2c2
1 Parent(s): 6632650

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +7 -7
  2. hyperparameters.json +1 -1
  3. ppo_pong.zip +1 -1
  4. replay.mp4 +0 -0
  5. results.json +1 -1
README.md CHANGED
@@ -1,29 +1,29 @@
1
  ---
2
  tags:
3
- - BreakoutNoFrameskip-v4
4
  - ppo
5
  - reinforcement-learning
6
  - stable-baselines3
7
  - deep-rl
8
  - atari
9
  model-index:
10
- - name: PPO Breakout
11
  results:
12
  - task:
13
  type: reinforcement-learning
14
- name: Breakout
15
  dataset:
16
- name: BreakoutNoFrameskip-v4
17
  type: atari
18
  metrics:
19
  - name: Mean Reward
20
  type: mean_reward
21
- value: 43.50 +/- 22.70
22
  ---
23
 
24
 
25
- # **PPO** Agent playing **BreakoutNoFrameskip-v4**
26
 
27
- This is a trained model of a **PPO** agent playing **BreakoutNoFrameskip-v4**.
28
 
29
  To learn to use this model and train yours, check the Deep Reinforcement Learning Course on [Hugging Face](https://huggingface.co/deep-rl-course).
 
1
  ---
2
  tags:
3
+ - PongNoFrameskip-v4
4
  - ppo
5
  - reinforcement-learning
6
  - stable-baselines3
7
  - deep-rl
8
  - atari
9
  model-index:
10
+ - name: PPO Pong
11
  results:
12
  - task:
13
  type: reinforcement-learning
14
+ name: Pong
15
  dataset:
16
+ name: PongNoFrameskip-v4
17
  type: atari
18
  metrics:
19
  - name: Mean Reward
20
  type: mean_reward
21
+ value: 20.40 +/- 0.92
22
  ---
23
 
24
 
25
+ # **PPO** Agent playing **PongNoFrameskip-v4**
26
 
27
+ This is a trained model of a **PPO** agent playing **PongNoFrameskip-v4**.
28
 
29
  To learn to use this model and train yours, check the Deep Reinforcement Learning Course on [Hugging Face](https://huggingface.co/deep-rl-course).
hyperparameters.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "BreakoutNoFrameskip-v4", "max_t": 1000, "n_evaluation_episodes": 10}
 
1
+ {"env_id": "PongNoFrameskip-v4", "max_t": 1000, "n_evaluation_episodes": 10}
ppo_pong.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d0b88f44849b456517b3344e164fc3712b7a469b89494c20e219b94668af2cd
3
  size 23100621
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75ee668a098c464252422975259c0b95430af7bd85a8132607b8bd4aa0494dd
3
  size 23100621
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "BreakoutNoFrameskip-v4", "mean_reward": 43.5, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-20T19:57:57.978604"}
 
1
+ {"env_id": "PongNoFrameskip-v4", "mean_reward": 20.4, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-20T20:04:52.548950"}