Commit ·
a13986f
1
Parent(s): 663cde7
Push agent to the Hub
Browse files- README.md +9 -10
- logs/events.out.tfevents.1676736737.corey-ubuntu.29057.0 +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 |
---
|
|
@@ -28,7 +28,7 @@ model-index:
|
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
```python
|
| 31 |
-
{'exp_name': '
|
| 32 |
'seed': 1
|
| 33 |
'torch_deterministic': True
|
| 34 |
'cuda': True
|
|
@@ -37,14 +37,13 @@ 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':
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
-
'
|
| 46 |
-
'
|
| 47 |
-
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 4
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
|
@@ -55,7 +54,7 @@ model-index:
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'CoreyMorris/lander-delete-me'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -105.96 +/- 18.63
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
```python
|
| 31 |
+
{'exp_name': 'ppo'
|
| 32 |
'seed': 1
|
| 33 |
'torch_deterministic': True
|
| 34 |
'cuda': True
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 100000
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
+
'num_envs': 16
|
| 43 |
+
'num_steps': 1024
|
| 44 |
'anneal_lr': True
|
| 45 |
+
'gamma': 0.999
|
| 46 |
+
'gae_lambda': 0.98
|
|
|
|
| 47 |
'num_minibatches': 4
|
| 48 |
'update_epochs': 4
|
| 49 |
'norm_adv': True
|
|
|
|
| 54 |
'max_grad_norm': 0.5
|
| 55 |
'target_kl': None
|
| 56 |
'repo_id': 'CoreyMorris/lander-delete-me'
|
| 57 |
+
'batch_size': 16384
|
| 58 |
+
'minibatch_size': 4096}
|
| 59 |
```
|
| 60 |
|
logs/events.out.tfevents.1676736737.corey-ubuntu.29057.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d2b772864c62711e5a98cfc1e34529d298d83ea4e4a5299a307459b7b32ee09
|
| 3 |
+
size 121024
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2883531737bbfa5a1f638c50bb86735c45f34aa9604c0896107b5d4b1f3ca99b
|
| 3 |
size 42817
|
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": -105.95638655063024, "std_reward": 18.627966001887124, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T11:12:44.214078"}
|