Hugging Face's logo

andylolu24
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
andylolu24 commited on
Commit
22ea671
•
1 Parent(s): 8a3b12e

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 275.50 +/- 83.08
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 64),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 200000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 442.00 +/- 104.62
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0003),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 500000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2202336912
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2797509801
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0003
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5475bcfacde9b3b5bb63a85f26b9b32e0c42afd3116e10e2e1c9e759613de8fd
3
- size 27225241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3d2717876372c51eeff72583d2bcbb992d4bc3cd4cd575959f10bd6950b856
3
+ size 27225242
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab278d18a9c1eb0c98c625d9d92e4ecaefa2a0390762ac5b00698f663d222b3
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffbe428dd915e0b23fdb0157e75b3f884c2b86ed75be4ce94859c833a6856b3
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:117e90859d3cecc8f3374d1150d8022ecca14e6cf1c5ec2774260ff31fcc9d6c
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303a43089c99693bd77a203500ac038b123819cdb61c526a45bf8079aca1d57b
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d255c9b1aa7bf77e2c0d0752f8c8dddaf52c4b372917a0b3a284c003dd687d08
3
- size 263020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15cf293ee8c9660f0112a68d713d636017822b37f0560a51f581db32d838f45
3
+ size 258322
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-17T18:46:32.815591"}
 
1
+ {"mean_reward": 442.0, "std_reward": 104.62313319720452, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-17T19:13:39.401748"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1e6f0765b8c069a0015642ebfd59c828ee5303a5b68c77de397a86656ec8543
3
- size 9349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31393649233a3860c21671cd4e0f8f0fac96e0541f6b28a138cfc09a01d4b4c
3
+ size 19796