Commit
•
55239e9
1
Parent(s):
a58b069
Push agent to the Hub
Browse files- README.md +62 -0
- logs/events.out.tfevents.1695548331.ca8ca8a1b9b6.3199.0 +3 -0
- model.pt +3 -0
- replay.mp4 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- LunarLander-v2
|
4 |
+
- ppo
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- custom-implementation
|
8 |
+
- deep-rl-course
|
9 |
+
model-index:
|
10 |
+
- name: PPO
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
type: reinforcement-learning
|
14 |
+
name: reinforcement-learning
|
15 |
+
dataset:
|
16 |
+
name: LunarLander-v2
|
17 |
+
type: LunarLander-v2
|
18 |
+
metrics:
|
19 |
+
- type: mean_reward
|
20 |
+
value: 150.91 +/- 75.99
|
21 |
+
name: mean_reward
|
22 |
+
verified: false
|
23 |
+
---
|
24 |
+
|
25 |
+
# PPO Agent Playing LunarLander-v2
|
26 |
+
|
27 |
+
This is a trained model of a PPO agent playing LunarLander-v2.
|
28 |
+
|
29 |
+
# Hyperparameters
|
30 |
+
```python
|
31 |
+
{'exp_name': 'ppo'
|
32 |
+
'gym_id': 'LunarLander-v2'
|
33 |
+
'learning_rate': 0.0003
|
34 |
+
'seed': 1
|
35 |
+
'total_timesteps': 5000000
|
36 |
+
'torch_deterministic': True
|
37 |
+
'cuda': True
|
38 |
+
'track': False
|
39 |
+
'wandb_project_name': 'ppo-implementation-details'
|
40 |
+
'wandb_entity': None
|
41 |
+
'capture_video': False
|
42 |
+
'env_id': 'LunarLander-v2'
|
43 |
+
'num_envs': 4
|
44 |
+
'num_steps': 1024
|
45 |
+
'anneal_lr': True
|
46 |
+
'gae': True
|
47 |
+
'gamma': 0.999
|
48 |
+
'gae_lambda': 0.98
|
49 |
+
'num_minibatches': 4
|
50 |
+
'update_epochs': 4
|
51 |
+
'norm_adv': True
|
52 |
+
'clip_coef': 0.2
|
53 |
+
'clip_vloss': True
|
54 |
+
'ent_coef': 0.01
|
55 |
+
'vf_coef': 0.5
|
56 |
+
'max_grad_norm': 0.5
|
57 |
+
'target_kl': None
|
58 |
+
'repo_id': 'FredericProtat/ppo-LunarLander-v2-u8'
|
59 |
+
'batch_size': 4096
|
60 |
+
'minibatch_size': 1024}
|
61 |
+
```
|
62 |
+
|
logs/events.out.tfevents.1695548331.ca8ca8a1b9b6.3199.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7a549f0d3df054b0f6d06db32415303fefbaad12f2a47ad064b99cc8a70e0ef
|
3 |
+
size 1756864
|
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3bd59314690aa59f4934e4cfe780493541a20c156d496ee902d980b9a0050a5
|
3 |
+
size 42597
|
replay.mp4
ADDED
Binary file (86.2 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": 150.90779060255167, "std_reward": 75.98746543957249, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-24T11:44:55.534319"}
|