Hugging Face's logo

Taratata
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Taratata commited on
Commit
152dd3c
•
1 Parent(s): de3c4c6

Initial commit

Browse files
Files changed (11) 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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 275.50 +/- 83.08
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -66,13 +66,13 @@ OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
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: 424.50 +/- 225.98
20
  name: mean_reward
21
  verified: false
22
  ---
 
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.1),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 500000.0),
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
- - 430524495
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 724492016
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -6,7 +6,7 @@
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.01
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.1
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 500000.0
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:daa605edf2a964df7bcfa5ddde1ba57ab29ec27478765fe375de0f093d2ac861
3
- size 13719746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23611ced17798aeeeab94d23edda8fdd53231435905a49838a16ecff20120c74
3
+ size 27224291
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 sha256:5f4b6b3ce249425e0e3fac61f7b9da129072f10a5b2377f54b5223f96950ece5
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19be310625c2a47cedc485d6ae866e19ba85cbc314d070ef9c7d2d3af851509c
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd564ab290f6f8186063a514a0acb0e5f3beca4fc212f3f0e4f81c35975c409
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,6 +2,6 @@
2
  - Python: 3.8.10
3
  - Stable-Baselines3: 1.8.0a2
4
  - PyTorch: 1.13.1+cu116
5
- - GPU Enabled: True
6
  - Numpy: 1.21.6
7
  - Gym: 0.21.0
 
2
  - Python: 3.8.10
3
  - Stable-Baselines3: 1.8.0a2
4
  - PyTorch: 1.13.1+cu116
5
+ - GPU Enabled: False
6
  - Numpy: 1.21.6
7
  - Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa6a1f28e357785d754b2769d1539f69db8d8cc9b953475f14f2f15f30761f4
3
- size 263235
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d846f986956069c78af14cf67fc3410797c64d71b33d42557cbfb4fedc825d
3
+ size 250993
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T16:30:44.462891"}
 
1
+ {"mean_reward": 424.5, "std_reward": 225.980640763761, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-17T16:19:16.881356"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b62ef5f8de2296ab5ed2fec513f9642ff6af753381821e5c90c5f6ce92259309
3
- size 5832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e3501c216359d8de997e538305b5c76189232750d26db5706b65b9ac549e08
3
+ size 22613