Hugging Face's logo

JYC333
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
JYC333 commited on
Commit
2553cc2
·
1 Parent(s): 0fb4fa5

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +2 -2
  3. config.yml +1 -1
  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: 698.50 +/- 231.68
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -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: 789.50 +/- 355.50
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 10000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
- - logs/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 4118413073
58
  - - storage
59
  - null
60
  - - study_name
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - ./rl-baselines3-zoo/logs/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1630278430
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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 sha256:5667c71db2c338ac002766dd5fbdddc823f4f0f66e54c7d8fccc5be33e134630
3
- size 27225047
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da42080a02527022afd901799601dded16cc070da270e3e254ac3944d43cb1dd
3
+ size 27225052
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 sha256:5838672ad9b89dde72080d74e1bc0ff2eb7ed4ecbdc83c3448a4e98d8a21e095
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf6005dc43d63adf81872789ab7d3c9fac30c2067066358cdc35a0d47942ae7
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:d1acf70ba89bdcf4f93fa82341725f4aa505fb947bdf995b1536bc4a151ebaf0
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7283e86c7434ee99203cf66acaa69cc734de2dda8a671d3745159ff8e5468dd3
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b262ee66359c35498f5307f9ae4113e74179a3203971d78c9cdd5ff9baec854
3
- size 186614
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91eaca00c3bfd8948d41f811cda93859288f88a57cb4054602c0194531551552
3
+ size 212471
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 698.5, "std_reward": 231.6791963038546, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T18:10:29.484168"}
 
1
+ {"mean_reward": 789.5, "std_reward": 355.50281292839304, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-03T17:35:02.968316"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67930b60acf06ca0f3d3e3bf2fccd2a9686bf90d4c0e5bfa81e4eaed7e6924ec
3
- size 38622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4cb54116a5b85e55e4dcb8d916ab02b84b514ea8eaeb14e24b264522d9676d
3
+ size 266717