Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1742872762.j-sim.36625.0 +3 -0
- model.pt +1 -1
- replay.mp4 +2 -2
- 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 |
---
|
|
@@ -37,19 +37,19 @@ model-index:
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
-
'total_timesteps':
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
| 45 |
-
'gae':
|
| 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':
|
| 53 |
'ent_coef': 0.01
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 169.18 +/- 109.37
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 1000000
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
| 45 |
+
'gae': False
|
| 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': False
|
| 53 |
'ent_coef': 0.01
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
logs/events.out.tfevents.1742872762.j-sim.36625.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6c91f4bf1ef6d1f7b59c36607e0e24007d653ac3e60b048a580c4bf7db1abdd
|
| 3 |
+
size 1282073
|
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 sha256:712bbb1c6a715baa14a19b8d985a772994a6a7898851f83e06aab3e4e4211041
|
| 3 |
size 43026
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93d70aabdcd811ab34fc9595d61d4b44c0929ae713f11b1be15bde45a9bc36ea
|
| 3 |
+
size 167692
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "LunarLander-v2", "mean_reward":
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": 169.1831155763707, "std_reward": 109.37471193874651, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-24T20:33:52.946113"}
|