Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1711128331.tikhon-XPS-15-9570.17160.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -17,7 +17,7 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value: -
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
@@ -40,22 +40,22 @@ model-index:
|
|
40 |
'total_timesteps': 50000
|
41 |
'learning_rate': 0.0003
|
42 |
'num_envs': 12
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
-
'num_minibatches':
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
-
'clip_coef': 0.
|
52 |
'clip_vloss': True
|
53 |
'ent_coef': 0.01
|
54 |
'vf_coef': 0.5
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'TikhonRadkevich/ppo_v2_LunarLander-v2'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -219.94 +/- 117.49
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
40 |
'total_timesteps': 50000
|
41 |
'learning_rate': 0.0003
|
42 |
'num_envs': 12
|
43 |
+
'num_steps': 1000
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
+
'num_minibatches': 64
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
+
'clip_coef': 0.0
|
52 |
'clip_vloss': True
|
53 |
'ent_coef': 0.01
|
54 |
'vf_coef': 0.5
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'TikhonRadkevich/ppo_v2_LunarLander-v2'
|
58 |
+
'batch_size': 12000
|
59 |
+
'minibatch_size': 187}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1711128331.tikhon-XPS-15-9570.17160.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c9be86839f352ba51532a2e80aec59cb933253b1d9a5ee19722b47696484bc4
|
3 |
+
size 62736
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42898
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c9e6099697f90f7d33320a98e1d3479dd0fad4a3f4499f096daf2e94dc058dc
|
3 |
size 42898
|
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": -
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -219.9420669995803, "std_reward": 117.48707823393356, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T20:25:45.522023"}
|