Hugging Face's logo

paicup09
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
paicup09 commited on
Commit
f79768a
·
1 Parent(s): 9f8256c

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  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: 540.00 +/- 105.69
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -58,19 +58,19 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
- ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 6e-05),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 700000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
- ('target_update_interval', 1000),
74
  ('train_freq', 4),
75
  ('normalize', False)])
76
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 542.00 +/- 152.14
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
+ ('buffer_size', 120000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 7e-05),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 900000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
+ ('target_update_interval', 900),
74
  ('train_freq', 4),
75
  ('normalize', False)])
76
  ```
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1605092063
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2699922974
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,16 +14,16 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 6.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 700000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 1000
28
  - - train_freq
29
  - 4
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 120000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 7.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 900000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
+ - 900
28
  - - train_freq
29
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdfc4da78ba72dcbeff2d9e59d9aebe5999ee2a7b8405bed64449d14c350c420
3
- size 27224791
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5dcee4abc1be008b849b801877de0231a0fd40c3579f59102f3340bfc2d3bb
3
+ size 27224790
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:d3268e11ee68d22f35e03aacc17745d9d5233f1d81103ba03890216e1968f072
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1083c25fd1e80e1f96ae86cb63b80c6ed3e6dfb085404724c2c3484a4376b05
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d5c7471a899e1f9b931dbf637c9b212913024ba66719efa13a080c62e956dc4
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9afb9fc4ab5f1ec30d02fe9dbc4e900bef9230476ed54fbcbd8d830998828ac
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93eaccedb044f58a2cf76576687746a84f10eb7dd725dae1eb66404b665f2d65
3
- size 201831
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373cf67558da5b74e3054e99f006e9c50eabce3d834756ea670fd10532c989f9
3
+ size 197209
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 540.0, "std_reward": 105.6882207249228, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T08:35:58.716820"}
 
1
+ {"mean_reward": 542.0, "std_reward": 152.1380951635717, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T15:36:12.285870"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005ca16fc89f58bd9b6559f1296ba38d113c03d643a00b9779f381eec9f3ba85
3
- size 30221
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7dd11f7dc9329365aecafdfbe5bd322f48dd202bf8dbd788d9a020cec3b19c3
3
+ size 34949