Push agent to the Hub
Browse files- README.md +11 -11
- logs/events.out.tfevents.1725113283.bf6224b6eef2.7686.0 +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 |
---
|
|
@@ -37,25 +37,25 @@ model-index:
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
-
'total_timesteps':
|
| 41 |
-
'learning_rate':
|
| 42 |
'num_envs': 4
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
-
'gamma': 0.
|
| 47 |
-
'gae_lambda': 0.
|
| 48 |
-
'num_minibatches':
|
| 49 |
-
'update_epochs':
|
| 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': 'Cryxim/ppo-LunarLanderV2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -158.41 +/- 89.51
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 50000
|
| 41 |
+
'learning_rate': 2e-05
|
| 42 |
'num_envs': 4
|
| 43 |
+
'num_steps': 256
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
+
'gamma': 0.97
|
| 47 |
+
'gae_lambda': 0.93
|
| 48 |
+
'num_minibatches': 5
|
| 49 |
+
'update_epochs': 3
|
| 50 |
'norm_adv': True
|
| 51 |
+
'clip_coef': 0.2
|
| 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': 'Cryxim/ppo-LunarLanderV2'
|
| 58 |
+
'batch_size': 1024
|
| 59 |
+
'minibatch_size': 204}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1725113283.bf6224b6eef2.7686.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f64f39abc7c843d0c2f6eb118eae585c068f781d2ebdfd42bac923adff703ab
|
| 3 |
+
size 90064
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43026
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:044d2ba3f43cc3558664ad6be3f6fd78a0968541a2d3b218ebbd41de548a51eb
|
| 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": -
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -158.40772154424025, "std_reward": 89.510746105138, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-31T14:08:40.723653"}
|