Hugging Face's logo

Clawoo
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Clawoo commited on
Commit
802ca76
·
1 Parent(s): 800d084

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 +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: 756.50 +/- 364.25
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -58,7 +58,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 32),
61
- ('buffer_size', 120000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1500000.0),
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: 546.00 +/- 263.66
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 32),
61
+ ('buffer_size', 110000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 1000000.0),
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
- - 815765429
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2169936928
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 120000
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
- - 1500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 110000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
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 sha256:7ff5868e1fb1916f9a424dc31a30a9a8fb561b569b4a4428a4fee71409136e5a
3
  size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827edb60fed5505eaec61c1fbebd7a9b7903809ea29e4ab8f6af2eb814a60d0a
3
  size 27224788
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:ef70198119241971b000899477434c310526f556f4829e113bd67b73d4aad0a5
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc371a5627da0aabce9de2587d17c153b1312e5b0879cde034a0bb2a34bab84
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:b14f9882d2261209e207862dc74f3befc2b8a90104ac056d09f5d2fc56478338
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbbec822cf6d8acea898e72243b401a973268a43a7eab0a6eb48b3a51c76f21c
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65b567cd2c9c22eafb98b4fa6efdc3506f46330437476d84127fcd8cbd75159d
3
- size 190983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e128e7fdd26743a77d0c9cdd013f50546a9265f2a7a6b9107a43acee1461b8a
3
+ size 203282
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 756.5, "std_reward": 364.2530027329905, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T15:16:16.825514"}
 
1
+ {"mean_reward": 546.0, "std_reward": 263.66455962074235, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T15:16:35.811259"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de029212340d4eff0d5123539b235daeb14b8b3221d80975b90197244a17b066
3
- size 49595
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3c2c8d3136b8a30313a73cfa10089c28cff0746e17d26761c4a914ff6dfc44
3
+ size 36270