Hugging Face's logo

npit
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
npit commited on
Commit
4e117e3
·
1 Parent(s): c3676bf

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +4 -4
  2. args.yml +1 -3
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 374.00 +/- 214.89
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,8 +62,8 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
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),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
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: 583.50 +/- 161.15
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 80000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
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
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1380215811
58
  - - storage
59
  - null
60
  - - study_name
@@ -79,5 +79,3 @@
79
  - sb3
80
  - - wandb_tags
81
  - []
82
- - - yaml_file
83
- - null
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3943025236
58
  - - storage
59
  - null
60
  - - study_name
 
79
  - sb3
80
  - - wandb_tags
81
  - []
 
 
config.yml CHANGED
@@ -1,8 +1,8 @@
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
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 80000
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:bb5236c0c281a45afe27090c0d2206f8b431b761b6bb1ce9619015e02a69c170
3
- size 13719748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4208197e666bc9199f0b31755d631fc0b9743ca576a7fc73f6c84a70be24930
3
+ size 27224860
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.7.0a12
 
1
+ 1.8.0
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:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a19882aa475d3e8368bdb0b947ce512a927413eec4d2e3c50092eee36d74877
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:f9dff6cb0bf53f0d47b9315c9d7df48ea87c640bbeeb81be1274fd0ee5281b55
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466ae47fb1461a430a517c134024cce38aebf113f3bba6866a6814a6f6dcca7e
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- - OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
- - Python: 3.8.16
3
- - Stable-Baselines3: 1.7.0a12
4
- - PyTorch: 1.13.0+cu116
5
  - GPU Enabled: True
6
- - Numpy: 1.21.6
7
  - Gym: 0.21.0
 
1
+ - OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
+ - Python: 3.10.11
3
+ - Stable-Baselines3: 1.8.0
4
+ - PyTorch: 2.0.0+cu118
5
  - GPU Enabled: True
6
+ - Numpy: 1.22.4
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b231c3e33922a65189db4066e7414df0b5a66d5fa35017253dc63dd0d43b457
3
- size 233415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d8930625e242318d14af33497fba171f92a495a17e8372598a16a10013d57b
3
+ size 212464
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-08T20:39:41.460530"}
 
1
+ {"mean_reward": 583.5, "std_reward": 161.15287772795122, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-07T20:38:08.471925"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d001d9388fac2fd7e45d54303852a6b62e812a20535963c7273865577c6df668
3
- size 5817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6659f3e24718ea84f652b2c266e293c1855b72d6e6c8bddea86e28443a86a3f
3
+ size 37134