Hugging Face's logo

dogpizza
/
Deep-Reinforcement-Learning_Unit3_dqn-SpaceInvadersNoFrameskip-v4-v2

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
dogpizza commited on
Commit
21e852c
·
verified ·
1 Parent(s): d4be1ef

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +2 -2
  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. results.json +1 -1
  9. 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: 153.00 +/- 69.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,8 +63,8 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 16),
67
- ('buffer_size', 50000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 16),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0003),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 462.50 +/- 212.43
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0003),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 100000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2486056240
60
  - - storage
61
  - null
62
  - - study_name
@@ -66,7 +66,7 @@
66
  - - track
67
  - false
68
  - - trained_agent
69
- - ''
70
  - - truncate_last_trajectory
71
  - true
72
  - - uuid
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1683680187
60
  - - storage
61
  - null
62
  - - study_name
 
66
  - - track
67
  - false
68
  - - trained_agent
69
+ - logs//dqn/SpaceInvadersNoFrameskip-v4_4/best_model.zip
70
  - - truncate_last_trajectory
71
  - true
72
  - - uuid
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 16
4
  - - buffer_size
5
- - 50000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
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
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 100000.0
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:e60243da0607b78a2eaca106ae00eb045faff64ac09ea03e5b8f992f50cdfcd2
3
- size 27221023
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89014eef9b767693e66ba2f71d2537844f9701f9f0041a3be558b643c4967840
3
+ size 27221019
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 sha256:4ae747a5bc8ef9953b435ae8e23fac7a81a27ca937ee36e264211a4e66a7d833
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8290800f7b528883e808058b01d1c169bafd897a4e726fb8ddf39a02802788cb
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:a80f53ed9e2ae0413a85000811a8e0d56051d604bcc2ded8d51d6e3cdfa23a49
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59c4bb4bf65788b91e19ea103c0cfd61a101d316a3b09e4d574ac45b66d9409
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 153.0, "std_reward": 69.9714227381436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-12T20:14:24.621617"}
 
1
+ {"mean_reward": 462.5, "std_reward": 212.42940003681224, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-12T20:24:15.591279"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3201ac08025c301e2f036fc32af5251bf7743f9f2f461cba022dfa958fb5fe8f
3
- size 36970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212912e4a047b5f11cce835e559b95552fe0c44eb0e23ba4ed62a96172b1228f
3
+ size 5768