Hugging Face's logo

benjyd
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
benjyd commited on
Commit
b906638
·
verified ·
1 Parent(s): 1c1a0fa

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +3 -3
  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. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +4 -4
  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: 616.50 +/- 185.42
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 710.00 +/- 238.40
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 10000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,15 +56,15 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 439235920
60
  - - storage
61
  - null
62
  - - study_name
63
  - null
64
  - - tensorboard_log
65
- - ''
66
  - - track
67
- - false
68
  - - trained_agent
69
  - ''
70
  - - truncate_last_trajectory
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1632485984
60
  - - storage
61
  - null
62
  - - study_name
63
  - null
64
  - - tensorboard_log
65
+ - runs/SpaceInvadersNoFrameskip-v4__dqn__1632485984__1738801755
66
  - - track
67
+ - true
68
  - - trained_agent
69
  - ''
70
  - - truncate_last_trajectory
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 sha256:7523b4980323619bb2742949a2acc7f68059981014f385d3a16d62f54bac68ba
3
- size 27220716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be20c6a1c3938bba48a00580eb379b8d2b64991de85001b9fa36c7c4a520935
3
+ size 27221642
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 sha256:1aab1d9a700e23964eb75013323f36b4ec056b8112add72a32604fb73832aac0
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5b1dbf1c039883c2cf08473700b36aec51d916b7e7663fcdab904d5013749e
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c347f7034a12341c31de12fd139e685437952a1e8a84e96e6f2a558bfc4579e
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3302b2739928349d1d1dacfe7ed388de56f056be9b5bb6ffdd49244d83416fe
3
  size 13505370
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,8 +1,8 @@
1
- - OS: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Tue Nov 5 00:21:55 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.5.0
4
- - PyTorch: 2.5.1+cu124
5
  - GPU Enabled: True
6
- - Numpy: 1.26.4
7
- - Cloudpickle: 3.1.0
8
  - Gymnasium: 1.0.0
 
1
+ - OS: Linux-6.8.0-52-generic-x86_64-with-glibc2.39 # 53-Ubuntu SMP PREEMPT_DYNAMIC Sat Jan 11 00:06:25 UTC 2025
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.5.0
4
+ - PyTorch: 2.6.0+cu124
5
  - GPU Enabled: True
6
+ - Numpy: 2.2.2
7
+ - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.0.0
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 616.5, "std_reward": 185.41911983395886, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-02T15:57:33.550878"}
 
1
+ {"mean_reward": 710.0, "std_reward": 238.4009228170059, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-06T10:33:01.697652"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7eae556e13696eeaa72a3393ef38b9bb5f4532ede4f8c61e5bf107d2c52d13c
3
- size 38459
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97ee2852906f8b5d8d963e538891b3af6f4cf91a5f76b6295e6e41c49d638bd
3
+ size 276475