Hugging Face's logo

bjarlestam
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
bjarlestam commited on
Commit
04ebf5d
·
1 Parent(s): c597659

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 +2 -2
  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: 289.00 +/- 149.60
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ 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', 70000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 32),
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', 200000.0),
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: 274.50 +/- 31.50
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 70000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 100000.0),
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
- - 1252897489
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3281825993
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
  - 70000
6
  - - env_wrapper
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 70000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 100000.0
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:f9603d8c3a1a68a83c7ebb68c8bef1b050d4a0f3706dc93fc28e090e7b01d6f7
3
- size 27224803
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a7419c106fa1860164b24d424da53af0942e44042be900de1f9177e90b5f13
3
+ size 13719746
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 sha256:82b7359c840656f03b09d05e9d1eca0ec8d77904db609c1c9e7b498ce63bee04
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8d25e1700fa8db131974bc76fc6bd98bdec67fae1809f8c8c0aef0df992089
3
+ size 687
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8264fd2a289de89ff2ba87e0e757c396628ad0d7f66d7f8701eb5cd1de9f5f4d
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bdf045013f2aa8af45f27253daf035524006c8b75d3aa3a3e75368dfbef32c
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69b45095e4c15af49a0cbcadd711be13071884635ba80769d6092a6964a2fe2d
3
- size 249219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba2ab7031f7061f065c3d5bc1de3dcfb9536d40b9bccd2413c48c7909f59ea3
3
+ size 261744
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 289.0, "std_reward": 149.59612294441322, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-30T22:54:46.090403"}
 
1
+ {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-30T23:01:15.240333"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e2a25e7daeb986d5a09a6b44897286d0c8e14886f49de214a9bc2143e8198ae
3
- size 9759
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b311c0e9bda07e6fc9c17a578efe773aa2666e7f28b3847bc8d58c135c506f65
3
+ size 5820