Hugging Face's logo

ArneL2206
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ArneL2206 commited on
Commit
e9b2ec7
·
1 Parent(s): 309ac28

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: 438.00 +/- 104.12
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,17 +57,17 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
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', 0.00025),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 604.00 +/- 144.44
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 32),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
+ ('exploration_fraction', 0.025),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 10000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2110961579
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3595287759
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
@@ -8,17 +8,17 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.00025
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
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
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.025
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
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 sha256:280fc3afe855948652b8e91c15c100740ed150a95a7f7da9102a1292aa8ec087
3
- size 27224933
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1b40b59b45adba7a4b9c03bb3f4fad39fd7264370402e0002f0b19a6106955
3
+ size 27224942
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 sha256:666e0a3022e3ea38c33f83aa8ad5ac95a9912723116dd3940f4ed8741a1f9358
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2626b6828caa9311635cb51c26b45d1f4bc58a3231fd7058941798f849352f
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5cca039e338439bd5bfb76d8371553ff32e5c80520d8dab6fb87270cc6d14a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166331d0f60a353e57cbb057413ef9cee51df6f2417dfdb9c21a7bd60e55a2b4
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ca72c9d925d2e068b15fb78bc56080949d5b85f6ba7629072b814a3bf436369
3
- size 190786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6c19da39e56d69f2180ea3ceeb4388606f9edf496cc3fc4f5ec5416a7bfc07
3
+ size 201780
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 438.0, "std_reward": 104.12012293500234, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-19T22:48:55.231354"}
 
1
+ {"mean_reward": 604.0, "std_reward": 144.4437606821423, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T20:23:28.595792"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4283a1fad9445a2555fa4b07d2b09468d43e32e31d9acc9cbeddfe4d585afc37
3
- size 34353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75a14fa6b6f4d33aee9cc07255c0585869bf1587e2d71baba09cb9d977982c3
3
+ size 79984