Push agent to the Hub
Browse files- README.md +8 -8
- logs/events.out.tfevents.1725113605.bf6224b6eef2.9168.0 +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 |
---
|
|
@@ -38,17 +38,17 @@ model-index:
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
-
'learning_rate': 0.
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 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
|
|
@@ -56,6 +56,6 @@ model-index:
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'Cryxim/ppo-LunarLanderV2'
|
| 58 |
'batch_size': 512
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -149.31 +/- 89.61
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
+
'learning_rate': 0.00025
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
+
'gamma': 0.99
|
| 47 |
+
'gae_lambda': 0.95
|
| 48 |
+
'num_minibatches': 4
|
| 49 |
+
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
+
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
| 53 |
'ent_coef': 0.01
|
| 54 |
'vf_coef': 0.5
|
|
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'Cryxim/ppo-LunarLanderV2'
|
| 58 |
'batch_size': 512
|
| 59 |
+
'minibatch_size': 128}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1725113605.bf6224b6eef2.9168.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:308c094a8cd756e671fa58ea72322d05ceb6f18ca5a513cf37bb3a632a03e742
|
| 3 |
+
size 109718
|
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:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
|
| 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": -149.31477407336644, "std_reward": 89.60859841431072, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-31T14:14:08.428212"}
|