Hugging Face's logo

mikolaj-mialkowski
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
mikolaj-mialkowski commited on
Commit
3b3d3df
•
1 Parent(s): 89fbb86

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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: 247.50 +/- 86.61
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
- ('buffer_size', 10000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 10000),
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: 716.50 +/- 260.89
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
 
71
  ('frame_stack', 4),
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
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3120090229
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1175693780
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
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 sha256:6cdd4f6c1c5acadb0cbd1ac365c1f32cf27b541bdcb3d1a89217e9cd19dd9596
3
- size 27219791
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30aa77b0ce224245295ebbb0a9578e65e712db8302de76cb2356466df969c6e
3
+ size 27219797
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 sha256:96b0a3b25ab6353b6f25a0b0130eae14c42fd8b661563ab03b3957200786af29
3
  size 13505852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5368726b438c0834f203eb271afa2da4c00009a41f8fcffc9b41de0cd6a03d38
3
  size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61961baffdf8302f5c9acf168f7b95cd6c6359692a52119958385dc64adf6f5b
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87ebb2e820d49b15b1c9b93ca6b155154d56bfb101867d180c520fb2804d9fa
3
  size 13505178
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81b4f2db0c965e41c7cf26080b70edbe893d1e4457a4f36c01a5a9e6bc66821f
3
- size 268429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e69302c3c1e77a8ad61cf70522fca319194fd988b01346f81e1cc82a476cba8
3
+ size 222306
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 247.5, "std_reward": 86.60975695613052, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-28T23:34:06.900912"}
 
1
+ {"mean_reward": 716.5, "std_reward": 260.8931773734223, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-29T08:48:54.008651"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4c5aa1a26167fb2dbf32a8604d81d68a70ea3cfc2e0aafa857fa769f14edf93
3
- size 5413
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f28e288ae5483a70e9fd9ce0d47ac00d4d7dfbeea13ce1cfd56ff4210929ac
3
+ size 38202