Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1684316823.a66f9935aa06.6357.0 +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 |
---
|
|
@@ -38,7 +38,7 @@ 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
|
|
@@ -51,9 +51,9 @@ model-index:
|
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
| 53 |
'ent_coef': 0.01
|
| 54 |
-
'vf_coef': 0.
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
-
'target_kl':
|
| 57 |
'repo_id': 'bastienm/ppo-LunarLander-v2'
|
| 58 |
'batch_size': 512
|
| 59 |
'minibatch_size': 128}
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -141.85 +/- 84.48
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
+
'learning_rate': 0.0001
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
|
|
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
| 53 |
'ent_coef': 0.01
|
| 54 |
+
'vf_coef': 0.7
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
+
'target_kl': 0.003
|
| 57 |
'repo_id': 'bastienm/ppo-LunarLander-v2'
|
| 58 |
'batch_size': 512
|
| 59 |
'minibatch_size': 128}
|
logs/events.out.tfevents.1684316823.a66f9935aa06.6357.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca2c125fd88a5f63decafa10399ea353ba84eef5f64d4fe3584e090708b492f
|
| 3 |
+
size 113545
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ccb6d26406b5978527f4acc6ace5049ec72346888cc28152f871da9d7c380fb
|
| 3 |
size 42469
|
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": -141.84792999693533, "std_reward": 84.4795985643585, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T09:47:39.084448"}
|