Hugging Face's logo

asubiabre
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
asubiabre commited on
Commit
e96fe3b
•
1 Parent(s): a4ed702

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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: 306.50 +/- 177.31
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),
@@ -71,7 +71,7 @@ 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'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 605.00 +/- 178.61
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', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2325988835
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2536864303
58
  - - storage
59
  - null
60
  - - study_name
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
@@ -16,7 +16,7 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
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
  - 1000000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b683cbcd3205c526a5209ca103ffa646c98dfdc9ffb29da51a2bccaee8f0de2
3
- size 27224806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c279f801900338c7a66c8e70a8ba00e8ac27d820353dc1798961d08cffaf73
3
+ size 27224807
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:c5f4aff2f28ca6b5fd09338612a4fea7a9dab971843870e898d024c12c758765
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce7e64acf6d64147ed2f9e76a9d7655411d6946b13a56d564b3b10a400a4eb8
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:bcb2a54caaee48ec1860e325635a3105b81a3a782502af67a27e2e0162851d95
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1b63ee1089950c76cab994cf130b55982d97e58587dad8c6da4e9903ad11c2
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3240822e19d8ed536413d88ed9d91c160dcfbd5eddd3cf28aa86fe5c6ff80804
3
- size 228190
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f401f9fe7d7c46bf425301d734ba28cc790f7de1cf5cb83881be7b2a23edb562
3
+ size 205283
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 306.5, "std_reward": 177.31398703993997, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-26T17:31:29.132595"}
 
1
+ {"mean_reward": 605.0, "std_reward": 178.60571099491753, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-26T19:13:22.204855"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2245a7b003b97010ee40928a188b045706da1be0f7c96d0f149dfe67d4fc563
3
- size 40088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fe576df5dc9d22419ba7530a5043340a5fce9e154d75af08aa546701c09146
3
+ size 37146