Hugging Face's logo

LeKyks1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
LeKyks1 commited on
Commit
d790dd3
•
1 Parent(s): 63300c2

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 +1 -1
  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: 329.00 +/- 157.97
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', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -70,8 +70,8 @@ OrderedDict([('batch_size', 64),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.01),
74
- ('learning_starts', 5000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 231.00 +/- 112.47
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 16),
66
  ('buffer_size', 1000),
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', 0.001),
74
+ ('learning_starts', 1000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1349503411
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2729997739
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
  - 1000
6
  - - env_wrapper
@@ -14,9 +14,9 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.01
18
  - - learning_starts
19
- - 5000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 16
4
  - - buffer_size
5
  - 1000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
18
  - - learning_starts
19
+ - 1000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91cf37767276792105a402207de844658f3087b1a9209578e897ecaf9c9452f5
3
  size 27220128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d145acd06969158c9325e3830ffc0ba4246597a2219649e497498cca87da1e
3
  size 27220128
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:f612ea896e475882635029055f9e55aedd8711f8246e02595c4d34e484ad596b
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3109e99c3d354e251acd608235b6df00a65d6ce876f27c95db845db24742c7e6
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eebb5a6779e8018aafef12e5eeed4b2adcce244cd1fa4c847ff75c02c962ef97
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927379cfb09023e5b487e141a756ef7ba3bda3f109e44675d816b881feb915a0
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e402fa68302f9262ebfd7be784ce6ff6785b68f25d4aa3a86e2c515a7bbb11
3
- size 242628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77eb287ea30f803912f85cf9479669ba8604bc59e70d34d4afcccaff34bb080
3
+ size 253213
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T12:14:31.092873"}
 
1
+ {"mean_reward": 231.0, "std_reward": 112.46777316191515, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T17:44:14.961407"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216adcce2505ef54d5b2ccf6e1f0bd43dfa4c3c401813c6a1d2bae02e553626e
3
- size 4939
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620420aa7167b5c3872dae22bee9e5cd2c1267dedd7f93483d0eb8d26ea50b9c
3
+ size 5120