hpandana commited on
Commit
151d0d4
1 Parent(s): 85964e7

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -152.75 +/- 87.00
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -54,7 +54,7 @@ model-index:
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
- 'repo_id': 'hpandana/ppo-LunarLander-v2'
58
  'batch_size': 512
59
  'minibatch_size': 128}
60
  ```
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -167.88 +/- 82.93
21
  name: mean_reward
22
  verified: false
23
  ---
 
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
+ 'repo_id': 'hpandana/PPO-LunarLander-v2'
58
  'batch_size': 512
59
  'minibatch_size': 128}
60
  ```
logs/events.out.tfevents.1699463169.1091791c9574.1998.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee14edf9f33efd11bbddbe36dfa247807b69e0e5b43ce2002aee3f97e6ca0bf
3
+ size 110093
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
3
  size 43026
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": -152.75162167436775, "std_reward": 87.00497108441625, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-08T16:07:10.224987"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -167.8806502044256, "std_reward": 82.93359489765463, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-08T17:07:08.377871"}