trtd56 commited on
Commit
57f1c34
1 Parent(s): 7bcf83c

Push Reinforce agent to the Hub

Browse files
README.md CHANGED
@@ -11,7 +11,7 @@ model-index:
11
  results:
12
  - metrics:
13
  - type: mean_reward
14
- value: -138.17 +/- 94.17
15
  name: mean_reward
16
  task:
17
  type: reinforcement-learning
@@ -37,7 +37,7 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
 
11
  results:
12
  - metrics:
13
  - type: mean_reward
14
+ value: 103.08 +/- 43.38
15
  name: mean_reward
16
  task:
17
  type: reinforcement-learning
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
logs/events.out.tfevents.1659741186.005638f23f8c.833.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ea0a39c8089de0af52f3367bf298e6ec82766b1d6add81ad7b67028b456138
3
+ size 656258
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:633f99a5be1425b9bb78acedbd8f155afa914e7550ea09f7eacf5e08d615cfba
3
  size 42817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d533664311d019bac32c039bc8afe737ab3c75c6178d8082cf6a77e92acc86a0
3
  size 42817
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -138.16997918081066, "std_reward": 94.16888020946013, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-05T23:11:46.583161"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 103.07583089813492, "std_reward": 43.37872462393049, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-05T23:27:38.046826"}