Commit ·
227440f
1
Parent(s): e05749f
Push agent to the Hub
Browse files- README.md +7 -7
- logs/events.out.tfevents.1696843580.Anderss-MacBook-Pro-4.local.50649.0 +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 |
---
|
|
@@ -37,15 +37,15 @@ model-index:
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
-
'total_timesteps':
|
| 41 |
-
'learning_rate': 0.
|
| 42 |
-
'num_envs':
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.999
|
| 47 |
'gae_lambda': 0.98
|
| 48 |
-
'num_minibatches':
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
@@ -55,7 +55,7 @@ model-index:
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'anders0204/ppo-LunarLander-v2'
|
| 58 |
-
'batch_size':
|
| 59 |
'minibatch_size': 64}
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -170.70 +/- 111.53
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 10000
|
| 41 |
+
'learning_rate': 0.0001
|
| 42 |
+
'num_envs': 16
|
| 43 |
+
'num_steps': 1024
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.999
|
| 47 |
'gae_lambda': 0.98
|
| 48 |
+
'num_minibatches': 256
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'anders0204/ppo-LunarLander-v2'
|
| 58 |
+
'batch_size': 16384
|
| 59 |
'minibatch_size': 64}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1696843580.Anderss-MacBook-Pro-4.local.50649.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32b8696c9181053536befed30ea5c874266d689fe0b875f248726e91900ef2a3
|
| 3 |
+
size 737
|
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 sha256:3ab6453fc35b83b0e8911f34afd7efdc7f1c7cf68d74ed6753245ce8f594ba8f
|
| 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": -170.69846007731394, "std_reward": 111.52902773549665, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-09T11:26:26.235947"}
|