Commit ·
fa41cfc
1
Parent(s): e6ada9c
Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1694611172.9f4ebd18e9a9.5863.0 +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 |
---
|
|
@@ -41,7 +41,7 @@ model-index:
|
|
| 41 |
'capture_video': False
|
| 42 |
'env_id': 'LunarLander-v2'
|
| 43 |
'num_envs': 4
|
| 44 |
-
'num_steps':
|
| 45 |
'anneal_lr': True
|
| 46 |
'gae': True
|
| 47 |
'gamma': 0.999
|
|
@@ -56,7 +56,7 @@ model-index:
|
|
| 56 |
'max_grad_norm': 0.5
|
| 57 |
'target_kl': None
|
| 58 |
'repo_id': 'FredericProtat/ppo-LunarLander-v2'
|
| 59 |
-
'batch_size':
|
| 60 |
-
'minibatch_size':
|
| 61 |
```
|
| 62 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -126.11 +/- 43.68
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 41 |
'capture_video': False
|
| 42 |
'env_id': 'LunarLander-v2'
|
| 43 |
'num_envs': 4
|
| 44 |
+
'num_steps': 256
|
| 45 |
'anneal_lr': True
|
| 46 |
'gae': True
|
| 47 |
'gamma': 0.999
|
|
|
|
| 56 |
'max_grad_norm': 0.5
|
| 57 |
'target_kl': None
|
| 58 |
'repo_id': 'FredericProtat/ppo-LunarLander-v2'
|
| 59 |
+
'batch_size': 1024
|
| 60 |
+
'minibatch_size': 256}
|
| 61 |
```
|
| 62 |
|
logs/events.out.tfevents.1694611172.9f4ebd18e9a9.5863.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71781a027f3a238c51273dc2b6a252ad21ac90ae9f2a37db12be1461a1e23ef9
|
| 3 |
+
size 178104
|
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:cb39ce9580cc067bb8dba6b23c37848196e7e1ce4c8bfdc538ddc2c4e5896b44
|
| 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": -126.11117655502812, "std_reward": 43.67537665875438, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T13:20:34.805695"}
|