vwxyzjn commited on
Commit
ff0b88f
1 Parent(s): b7ad53f

pushing model

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: Pong-v5
17
  metrics:
18
  - type: mean_reward
19
- value: -20.50 +/- 0.50
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -32,7 +32,7 @@ found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/sebulba_ppo_
32
  To use this model, please install the `cleanrl` package with the following command:
33
 
34
  ```
35
- pip install "cleanrl[sebulba_ppo_envpool]"
36
  python -m cleanrl_utils.enjoy --exp-name sebulba_ppo_envpool --env-id Pong-v5
37
  ```
38
 
 
16
  type: Pong-v5
17
  metrics:
18
  - type: mean_reward
19
+ value: -20.40 +/- 0.66
20
  name: mean_reward
21
  verified: false
22
  ---
 
32
  To use this model, please install the `cleanrl` package with the following command:
33
 
34
  ```
35
+ pip install "cleanrl[jax,envpool,atari]"
36
  python -m cleanrl_utils.enjoy --exp-name sebulba_ppo_envpool --env-id Pong-v5
37
  ```
38
 
events.out.tfevents.1675614079.ip-26-0-128-121.2242486.0 → events.out.tfevents.1675614244.ip-26-0-128-121.2245265.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f49bdd0d0221a21c88305b3bd60847fa9e7ffee06720b66c3275a4e08b149262
3
  size 39173
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4b502eb043bb4939c51d419cc3560d0e5c794acf9fb5f5ffc8361cfc73eac83
3
  size 39173
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
sebulba_ppo_envpool.cleanrl_model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:767ca23ed40cc1462b7827d12935ad5d95b1fe2b12c9e4da1c16b090f3aeba45
3
  size 4378336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a38ade401b6608fba3b56897a8ba8ef47abe60c033f22c57ac5593eed995d76
3
  size 4378336
sebulba_ppo_envpool.py CHANGED
@@ -876,7 +876,7 @@ if __name__ == "__main__":
876
 
877
  repo_name = f"{args.env_id}-{args.exp_name}-seed{args.seed}"
878
  repo_id = f"{args.hf_entity}/{repo_name}" if args.hf_entity else repo_name
879
- push_to_hub(args, episodic_returns, repo_id, "PPO", f"runs/{run_name}", f"videos/{run_name}-eval")
880
 
881
  envs.close()
882
  writer.close()
 
876
 
877
  repo_name = f"{args.env_id}-{args.exp_name}-seed{args.seed}"
878
  repo_id = f"{args.hf_entity}/{repo_name}" if args.hf_entity else repo_name
879
+ push_to_hub(args, episodic_returns, repo_id, "PPO", f"runs/{run_name}", f"videos/{run_name}-eval", extra_dependencies=["jax", "envpool", "atari"])
880
 
881
  envs.close()
882
  writer.close()
videos/Pong-v5__sebulba_ppo_envpool__1__3aee0c3c-65de-40c9-b787-e4435047b414-eval/0.mp4 DELETED
Binary file (44.2 kB)
 
videos/Pong-v5__sebulba_ppo_envpool__1__859fb3f0-0595-46e5-afd6-dda7445846f6-eval/0.mp4 ADDED
Binary file (42.2 kB). View file