Hugging Face's logo

SwampMan
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
SwampMan commited on
Commit
75fe594
·
1 Parent(s): 5fed8be

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +3 -3
  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: 383.50 +/- 182.55
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
- ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
75
- ('n_timesteps', 1000000.0),
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: 591.00 +/- 154.43
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -32,7 +32,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - -1
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 631872910
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - ''
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
+ - 300000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2907747335
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - rl_trained/dqn/SpaceInvadersNoFrameskip-v4_1/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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:bf67b7864f39d47c4b2476e2b0d7ed14726d327bdb3bd05217d6e524924327b5
3
- size 27218385
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fef498197322bedab8c0b447767c18028a5d9559543ef1e5a3f7a04230f4e2
3
+ size 27218384
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 sha256:0c14374bb5a09655ed01d420779fd93546e296f5e4b08f90e9b132ef096b874b
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c753913aa81589c82c3813080e73d718c1e552e9962cebe6c34b23e5630fe4
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:af859e75fcad7aa6aa376075ab5d98b4bae842afd15411f7bae59bd0e23ca524
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e8c23c23299520fb8d6e17746e1ab0d253a80c322e8d8fa8f4a13ce6bef0f0
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa38d36b6ae06025436ba42635eed70ae1642991d0c5c106d901ead253daebf
3
- size 253554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7f3f6ca650a4cd0bc999ba768b2e2bcb4a526107e2853324db5688e23067e9
3
+ size 251409
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 383.5, "std_reward": 182.55204737279723, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T21:26:24.116874"}
 
1
+ {"mean_reward": 591.0, "std_reward": 154.4312144613258, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-03T20:37:29.852757"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e454dd7f8ca7c2d1308da1d2aac0b98d879d4891e1407fc7f321505b770c4c4b
3
- size 40299
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df732eccd0807831354ce3adba0f9a0c322eeba97e297d99c1697f2483d63492
3
+ size 11263