Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1696333322.c3a73f0993b6.15664.0 +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 |
---
|
|
@@ -32,7 +32,7 @@ model-index:
|
|
| 32 |
'gym_id': 'LunarLander-v2'
|
| 33 |
'learning_rate': 0.0003
|
| 34 |
'seed': 1
|
| 35 |
-
'total_timesteps':
|
| 36 |
'torch_deterministic': True
|
| 37 |
'cuda': True
|
| 38 |
'capture_video': False
|
|
@@ -40,8 +40,8 @@ model-index:
|
|
| 40 |
'wandb_project_name': 'cleanRL'
|
| 41 |
'wandb_entity': None
|
| 42 |
'repo_id': 'DarkRodry/unit8_LunarLander-v2'
|
| 43 |
-
'num_envs':
|
| 44 |
-
'num_steps':
|
| 45 |
'anneal_lr': True
|
| 46 |
'gae': True
|
| 47 |
'gamma': 0.99
|
|
@@ -55,7 +55,7 @@ model-index:
|
|
| 55 |
'vf_coef': 0.5
|
| 56 |
'max_grad_norm': 0.5
|
| 57 |
'target_kl': None
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 95.86 +/- 103.04
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 32 |
'gym_id': 'LunarLander-v2'
|
| 33 |
'learning_rate': 0.0003
|
| 34 |
'seed': 1
|
| 35 |
+
'total_timesteps': 1500000
|
| 36 |
'torch_deterministic': True
|
| 37 |
'cuda': True
|
| 38 |
'capture_video': False
|
|
|
|
| 40 |
'wandb_project_name': 'cleanRL'
|
| 41 |
'wandb_entity': None
|
| 42 |
'repo_id': 'DarkRodry/unit8_LunarLander-v2'
|
| 43 |
+
'num_envs': 16
|
| 44 |
+
'num_steps': 256
|
| 45 |
'anneal_lr': True
|
| 46 |
'gae': True
|
| 47 |
'gamma': 0.99
|
|
|
|
| 55 |
'vf_coef': 0.5
|
| 56 |
'max_grad_norm': 0.5
|
| 57 |
'target_kl': None
|
| 58 |
+
'batch_size': 4096
|
| 59 |
+
'minibatch_size': 1024}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1696333322.c3a73f0993b6.15664.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6002ef6974d59798daa632f0a51581f7aa78c85224b525208e0a743dbc1b5fb1
|
| 3 |
+
size 474842
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:477834892dd286fc8e419efdbb73646a5043bbe63923ba0cd773951735760c6b
|
| 3 |
size 42597
|
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": 95.85679868219687, "std_reward": 103.04192239300116, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-03T12:15:18.899772"}
|