Hugging Face's logo

kmposkid1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
kmposkid1 commited on
Commit
37938b0
•
1 Parent(s): 542494e

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: 265.00 +/- 66.03
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),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
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: 407.00 +/- 152.71
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 25000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 10000),
75
+ ('n_timesteps', 500000.0),
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
- - 877862620
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2394776282
58
  - - storage
59
  - null
60
  - - 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
@@ -18,7 +18,7 @@
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
+ - 25000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 10000
20
  - - n_timesteps
21
+ - 500000.0
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:c2d4fffd498c518b0597edf2691842f9c5c510d6a091df3e31625f4209716202
3
- size 27224801
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5c4c64b9064a6faacb7be668b8be7e5cb2edaf9dbac1055bf48322c9749ac5
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 sha256:481edffc43be9000b79396ccec4d9ac6a69904d030775442acb147952efc22ab
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984a48efb0101deed2900651bb87a56dd11d8cd7ff916bbead187c95584bcb8b
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a90dd03cae165964c3379e6307d81e0622b38bc092d88475d1198f4bf26c686
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2676906a600a3025bf5f1547847a9d9bfa0ed7370751d64ddb9174a0c09ad2e3
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99f6e63270cc88e01e448a73f9c3e2b9309fda7406aa98744cdf38c83525a9c0
3
- size 247378
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f04970a785ae9538204b42daf35f209518352c6eed98804325efe6eed4522f
3
+ size 188746
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 265.0, "std_reward": 66.03029607687671, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-10T21:46:44.135899"}
 
1
+ {"mean_reward": 407.0, "std_reward": 152.7121475194426, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-10T23:30:38.652198"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fc6e0a4d5ed0f532fdcea6a7b35ab3ee16ef13a2bff365ff6295a3d934bc2cd
3
- size 4997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fdf2e17ea71773df219207549263e33b7400527d8a34d6c19115874ce9ec5e6
3
+ size 22118