Hugging Face's logo

irow
/
ppo-LunarLander-v2

Reinforcement Learning
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files Metrics Community
irow commited on
Commit
e30957c
•
1 Parent(s): a205d54

Push agent to the Hub

Browse files
Files changed (5) hide show
  1. README.md +9 -9
  2. logs/events.out.tfevents.1684424458.irow-pc.69002.0 +3 -0
  3. model.pt +1 -1
  4. replay.mp4 +0 -0
  5. 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: -165.17 +/- 85.08
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -29,7 +29,7 @@ model-index:
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'ppo'
32
- 'seed': 653623
33
  'torch_deterministic': True
34
  'cuda': True
35
  'track': False
@@ -37,14 +37,14 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 1000000
41
- 'learning_rate': 1e-05
42
- 'num_envs': 64
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.999
47
- 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'irow/ppo-LunarLander-v2'
58
- 'batch_size': 8192
59
- 'minibatch_size': 2048}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -37.96 +/- 96.58
21
  name: mean_reward
22
  verified: false
23
  ---
 
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'ppo'
32
+ 'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
35
  'track': False
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
+ 'learning_rate': 0.00025
42
+ 'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.99
47
+ 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'irow/ppo-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1684424458.irow-pc.69002.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087c348d1c2b314a47b851727785eeca2ad5394673840c58590dbdbb9253f609
3
+ size 681311
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22ad6df793e172fb05cc80042f0b18b5bd480302a7774c920acc19aa16c00c51
3
  size 42817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c826bd7083becb825d82cc49162fcc449d4b7e7e8d295509334fa948ce9a48
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": -165.17162404995943, "std_reward": 85.08336394311924, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:39:15.349892"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -37.95519946808062, "std_reward": 96.58091375753992, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:49:10.854358"}