TikhonRadkevich commited on
Commit
40df7ff
1 Parent(s): 38dfed8

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: -61.11 +/- 15.76
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,15 +37,15 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 1000000
41
  'learning_rate': 0.0003
42
  'num_envs': 16
43
- 'num_steps': 8
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
  'gae_lambda': 0.98
48
- 'num_minibatches': 4
49
  'update_epochs': 2
50
  'norm_adv': True
51
  'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'TikhonRadkevich/ppo_v2_LunarLander-v2'
58
- 'batch_size': 128
59
- 'minibatch_size': 32}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 65.54 +/- 73.90
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 700000
41
  'learning_rate': 0.0003
42
  'num_envs': 16
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
  'gae_lambda': 0.98
48
+ 'num_minibatches': 256
49
  'update_epochs': 2
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'TikhonRadkevich/ppo_v2_LunarLander-v2'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 64}
60
  ```
61
 
logs/events.out.tfevents.1711132813.tikhon-XPS-15-9570.21570.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a05584b1316d7c26d1d3cefd1691746db672ed5a1f0c8f2f6cbcc74e01e3e5
3
+ size 274894
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a37c742a3e3809f5ace810eed55abe25e903de35f2f132f154e35f326dde0b
3
  size 80274
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d730dc01ad7c378351f31c286654269e842bb71b9151a9d6330ce52a60ce3df
3
  size 80274
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": -61.11161937070783, "std_reward": 15.76215602890775, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T21:38:44.394904"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 65.54271978298064, "std_reward": 73.89745225273381, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T21:49:16.499662"}