Hugging Face's logo

SteveSchmidt
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
SteveSchmidt commited on
Commit
5ba289f
•
1 Parent(s): be41ff3

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 +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: 217.50 +/- 70.12
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,12 +67,12 @@ OrderedDict([('batch_size', 32),
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', 150000.0),
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: 227.00 +/- 17.92
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.2),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 200000.0),
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
- - 2173406486
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1320498705
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 150000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 200000.0
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:bca7e2460a3d159671e6a35cf66028e8095d7335fc808a5696ac952080edb8a9
3
- size 27224802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d2f8afac92648b89a1959c47f5f166f301488300c8a7563d786004490d32ed
3
+ size 27224803
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:a0144a7bb0d62e3f878862f4dac4b34b354a094abee6949340554419203e7385
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a460a2c3dc52c4a20a64f5c66099827d9c1cad7ddd6af64ad3e4b37be50fde
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:ce1bf92850ad9a9ccf573b7684b1e339cbb945d4db010b47860ac02f71a73e91
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4866f5a9907c3e5e6f658d38b5fb0fba1b764262eb20edf139da3cf4e7aaee
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3547c0c7765d549c52a605bc0da3332317bbd722ab49e023aa30f9602dc31df4
3
- size 250186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983b686d8a0b87a1b20db9ee1d559a3e59cc2ffe2a4d97badb9e549b35500acf
3
+ size 260085
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 217.5, "std_reward": 70.11597535512146, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-14T17:44:52.893222"}
 
1
+ {"mean_reward": 227.0, "std_reward": 17.916472867168917, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-14T18:13:40.663848"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3f76fb7e3aade6685b7a39dd1cf63d05136937c53b1065187b2171b3818696
3
- size 7931
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac64407e8a32ac6f37c230cc49abcc27613d48feb8c28e8e449ab58bfd5a807
3
+ size 9806