Hugging Face's logo

MattStammers
/
appo-mujoco-swimmer

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
MattStammers commited on
Commit
d614137
•
1 Parent(s): 8c14c03

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .summary/0/events.out.tfevents.1695288708.rhmmedcatt-ProLiant-ML350-Gen10 +3 -0
  2. .summary/1/events.out.tfevents.1695288708.rhmmedcatt-ProLiant-ML350-Gen10 +3 -0
  3. README.md +1 -1
  4. checkpoint_p0/best_000007040_3604480_reward_227.091.pth +3 -0
  5. checkpoint_p0/checkpoint_000019352_9908224.pth +3 -0
  6. checkpoint_p0/checkpoint_000019544_10006528.pth +1 -1
  7. checkpoint_p1/best_000017880_9154560_reward_92.992.pth +3 -0
  8. checkpoint_p1/checkpoint_000019352_9908224.pth +3 -0
  9. checkpoint_p1/checkpoint_000019544_10006528.pth +1 -1
  10. config.json +6 -5
  11. git.diff +0 -0
  12. replay.mp4 +2 -2
  13. sf_log.txt +0 -0
.summary/0/events.out.tfevents.1695288708.rhmmedcatt-ProLiant-ML350-Gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32cd1d3e30390ac5ce27d5b5d45ca255273b228cca7b192fd92c1dd57d209627
3
+ size 1232538
.summary/1/events.out.tfevents.1695288708.rhmmedcatt-ProLiant-ML350-Gen10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7528a60d4ac6937cd2ad1fb43661505e0ee55a76aaba00673e65666f6bf23e9
3
+ size 890199
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: mujoco_swimmer
16
  metrics:
17
  - type: mean_reward
18
- value: 47.51 +/- 1.11
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: mujoco_swimmer
16
  metrics:
17
  - type: mean_reward
18
+ value: 114.30 +/- 17.80
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000007040_3604480_reward_227.091.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2dd2f55255038dc8d8984f90e1be9c06307ac80ed05f49f0e5cd30f686b5317
3
+ size 72959
checkpoint_p0/checkpoint_000019352_9908224.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8564971af12444e339bc5f05bdd481432a55903f9d599e52b99f5e4927b11854
3
+ size 73223
checkpoint_p0/checkpoint_000019544_10006528.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97cc3eea59c4d66e39889017c5f9fa8dd98647621b35fb544957e5aa4c464f22
3
  size 73223
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e139341f0285f5808dc8dd9891d2dadfda04097ac34c7dbb424fb05ad45c81ef
3
  size 73223
checkpoint_p1/best_000017880_9154560_reward_92.992.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c8fac25b27c8714e82acc347e691a25ad4b5ba764f9885d385e329d55347e4
3
+ size 72959
checkpoint_p1/checkpoint_000019352_9908224.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3544cd07465e01c33bd4be3d62cda0e19cc2a18d460428051e21b0925ce6e5af
3
+ size 73223
checkpoint_p1/checkpoint_000019544_10006528.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9db7e90219aa4d610903bd9e342d63d43a7ff34c4ca4bbffcd40883aa5bba1d8
3
  size 73223
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37542c37910afcd91462f12047f7ef3cf588a6f25ab307c950b63680c5aba2b
3
  size 73223
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "rollout": 64,
24
  "recurrence": 1,
25
  "shuffle_minibatches": false,
26
- "gamma": 0.99,
27
  "reward_scale": 1,
28
  "reward_clip": 1000.0,
29
  "value_bootstrap": true,
@@ -105,10 +105,10 @@
105
  "with_wandb": true,
106
  "wandb_user": "matt-stammers",
107
  "wandb_project": "sample_factory",
108
- "wandb_group": "mujoco_swimmer",
109
  "wandb_job_type": "SF",
110
  "wandb_tags": [
111
- "mujoco_swimmer"
112
  ],
113
  "with_pbt": false,
114
  "pbt_mix_policies_in_one_env": true,
@@ -122,13 +122,14 @@
122
  "pbt_target_objective": "true_objective",
123
  "pbt_perturb_min": 1.1,
124
  "pbt_perturb_max": 1.5,
125
- "command_line": "--env=mujoco_swimmer --experiment=Swimmer --train_dir=./train_dir",
126
  "cli_args": {
 
127
  "env": "mujoco_swimmer",
128
  "experiment": "Swimmer",
129
  "train_dir": "./train_dir"
130
  },
131
  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
132
  "git_repo_name": "not a git repository",
133
- "wandb_unique_id": "Swimmer_20230920_172455_968369"
134
  }
 
23
  "rollout": 64,
24
  "recurrence": 1,
25
  "shuffle_minibatches": false,
26
+ "gamma": 0.9999,
27
  "reward_scale": 1,
28
  "reward_clip": 1000.0,
29
  "value_bootstrap": true,
 
105
  "with_wandb": true,
106
  "wandb_user": "matt-stammers",
107
  "wandb_project": "sample_factory",
108
+ "wandb_group": "mujoco_swimmer_2",
109
  "wandb_job_type": "SF",
110
  "wandb_tags": [
111
+ "mujoco"
112
  ],
113
  "with_pbt": false,
114
  "pbt_mix_policies_in_one_env": true,
 
122
  "pbt_target_objective": "true_objective",
123
  "pbt_perturb_min": 1.1,
124
  "pbt_perturb_max": 1.5,
125
+ "command_line": "--algo=APPO --env=mujoco_swimmer --experiment=Swimmer --train_dir=./train_dir",
126
  "cli_args": {
127
+ "algo": "APPO",
128
  "env": "mujoco_swimmer",
129
  "experiment": "Swimmer",
130
  "train_dir": "./train_dir"
131
  },
132
  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
133
  "git_repo_name": "not a git repository",
134
+ "wandb_unique_id": "Swimmer_20230921_091703_025123"
135
  }
git.diff CHANGED
The diff for this file is too large to render. See raw diff
 
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab74aecee70e2f62487a0c55b7bd09df63ca7122f5e7f041c1ca03f3b544d28b
3
- size 5455287
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e98390194fc2f39b1144dc42e61fbdf42591a5b2e4db8d7bce95fb62590376
3
+ size 12351563
sf_log.txt CHANGED
The diff for this file is too large to render. See raw diff