Hugging Face's logo

jason1i
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jason1i commited on
Commit
de95820
·
1 Parent(s): 30a7529

Initial commit

Browse files
Files changed (9) 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.pth +1 -1
  7. replay.mp4 +2 -2
  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: 15.50 +/- 12.54
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,12 +62,12 @@ 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),
70
- ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.01),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 274.50 +/- 31.50
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 8),
66
  ('buffer_size', 100000),
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', 0.01),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1756302526
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1459184332
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -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
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 8
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e214ea06300af2839cd140fa0a6b378cd892e83eacf6ede2bf8468a2e4dbf6b
3
- size 13719742
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f00a9d537e9deb127eba8e413e9b2a69ab581f10c3d8a4ae16e2aa5f9f94263
3
+ size 13719741
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d63b8c00fdb23fcd06b9f21084480439ece92bba42a16571779650b0305fa9e7
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f73eba39c459fd249b3a798826b22272ce5d35a6a9ee6238dcaf1f3fe2768f3
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d4afaddf633990f3d270cf9e169f40ac375b39e821b996f71f99ba9161b17f7
3
- size 273553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e13a11a839fea521ecfd34a27ae00521e04cfb8dd63fb3e005e2d701b498e2b
3
+ size 261744
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T13:40:00.683838"}
 
1
+ {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T14:11:42.318452"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d54ea781371a2b2a69101825959ed70bbdefd233dfbb385275720f7932ad69e8
3
- size 5780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ca07ac91e458e903826c179ce59cf45fb2f6b9bf20c3014e16a8b873d7dd67
3
+ size 5903