Hugging Face's logo

bwalser
/
SpaceInvaders-v4-100k

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
bwalser commited on
Commit
8a637a4
·
verified ·
1 Parent(s): 7cdda64

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 +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: 253.50 +/- 33.92
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', 100000.0),
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: 833.00 +/- 296.43
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', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2098816971
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3515035951
60
  - - storage
61
  - null
62
  - - 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
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 100000.0
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
+ - 1000000.0
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 sha256:698c901f5245b18e355acb0a1abf742ccf433b185fa1ac32e072988ad17d1e71
3
- size 27220589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f09d0e7dcf00907c1be25c93c1dd57a9ec9058e19a385d2ead0e6bec9b875da
3
+ size 27220595
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:df590107deb0afc6800eea4023158a347d47f247f2a12406597da940f16a2cd3
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77e8f4576af9058c2e16c2ba73409c9f01d5c31c5601e4487cacee42c767d73
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:045df3a8f76f38eebd8ff2709c54959f80e80c5e1731b11fcceb1b32c7b1d659
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c4d9ef0a85ee5cdaef0adcc5e9f4091bf739c2291740e0de25c50345b4cb4f
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ccb87e390f7d32309ac71fc40f0154b86e4ba3b7ccae90f5ab80318537e7979
3
- size 246077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ae7676a12981bdd3fd88252ea1d4ab8a25ffc4ecf3d311ec8703948af950c8
3
+ size 208056
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 253.5, "std_reward": 33.915335764223244, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-28T08:00:40.229669"}
 
1
+ {"mean_reward": 833.0, "std_reward": 296.4304302867707, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-28T09:02:24.456762"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54df54c4f72112916b924448eb98934526d380a5ced0b123d4e485bfe76c40a1
3
- size 4986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63df5437ec0f651d83112278913103b04104a32364804051403058a28792df2
3
+ size 36998