Hugging Face's logo

erniechiew
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
erniechiew commited on
Commit
cf1f572
•
1 Parent(s): dd0f48d

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: 725.00 +/- 202.23
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,8 +57,8 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('batch_size', 32),
61
- ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 1021.50 +/- 314.04
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 64),
61
+ ('buffer_size', 250000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 30000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 157037041
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 658870614
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 250000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 30000000.0
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:f13d6943d43d2a771ef6c03a30c77ecc4aac5184ba5a8abd0474f05aed0accdf
3
- size 27225001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb116cb3ed736cf7f27b92e9149202e79b51db96fb2f37152d0f3cea6d266ad
3
+ size 27225006
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:bd5defdffe3c54dba58ef6fee4d7cc10862dbe10b8a9c1c8f65b230f28ca4805
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37cfef316e5d3f1bc9bdd6fe6f89746cec2662c622f6964dbb156abb9165682
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e1e0cf0017c19897b3a14e5bd6c5b7ce7467889bcada26ab93e306085e615a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16da6b6e058386d542fa08c59dd7a43281cb8b78c3be06ed3d21a2963bc33105
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a1d9a51887f3ef089027e8ed9968996552900e7a2275f0e63508e7b5c3c6508
3
- size 168098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87b4e7647167345a6d9a36bf6e41ac5503bd1dc4fd5577a20639df084686a4a
3
+ size 193826
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 725.0, "std_reward": 202.2251220793302, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-04T22:08:19.148079"}
 
1
+ {"mean_reward": 1021.5, "std_reward": 314.0386122756245, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-06T09:34:59.294003"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fbca62c636e3f0f65a9583d7c884bc15e41d1ae92b1c0f955104c0b5740c7f2
3
- size 36620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a066e2a5d6e0dc27d34fe099dd2821afec97570ae71be9b95d3c9cf171d811a9
3
+ size 781924