nithiroj commited on
Commit
6286650
1 Parent(s): fb38bdf

Push Reinforce agent to the Hub

Browse files
README.md CHANGED
@@ -9,16 +9,17 @@ tags:
9
  model-index:
10
  - name: PPO
11
  results:
12
- - metrics:
13
- - type: mean_reward
14
- value: 166.00 +/- 55.22
15
- name: mean_reward
16
- task:
17
  type: reinforcement-learning
18
  name: reinforcement-learning
19
  dataset:
20
  name: CartPole-v1
21
  type: CartPole-v1
 
 
 
 
 
22
  ---
23
 
24
  # PPO Agent Playing CartPole-v1
@@ -54,7 +55,6 @@ model-index:
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
- 'virtual_display': True
58
  'repo_id': 'NithirojTripatarasit/ppo-CartPole-v1'
59
  'batch_size': 512
60
  'minibatch_size': 128}
 
9
  model-index:
10
  - name: PPO
11
  results:
12
+ - task:
 
 
 
 
13
  type: reinforcement-learning
14
  name: reinforcement-learning
15
  dataset:
16
  name: CartPole-v1
17
  type: CartPole-v1
18
+ metrics:
19
+ - type: mean_reward
20
+ value: 191.60 +/- 75.81
21
+ name: mean_reward
22
+ verified: false
23
  ---
24
 
25
  # PPO Agent Playing CartPole-v1
 
55
  'vf_coef': 0.5
56
  'max_grad_norm': 0.5
57
  'target_kl': None
 
58
  'repo_id': 'NithirojTripatarasit/ppo-CartPole-v1'
59
  'batch_size': 512
60
  'minibatch_size': 128}
logs/events.out.tfevents.1662593036.c631b7690fa4.883.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16283c1c5c6bc40acf78a96282d588897351c2d3509e8f6220c69eaa6c7267d8
3
+ size 50365
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:615063e1c901e83f6483e95e25739786a9c37a58a7e03e55a1c56f95f7e1493a
3
- size 40129
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befd74b53822918297bf329aeeada1b79a74d407ba3283356a68f6d4df52648a
3
+ size 40257
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "CartPole-v1", "mean_reward": 166.0, "std_reward": 55.22499434133063, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-08T05:38:57.571085"}
 
1
+ {"env_id": "CartPole-v1", "mean_reward": 191.6, "std_reward": 75.81187242114522, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-07T23:24:28.838257"}