bwilkie commited on
Commit
0eb0ceb
·
1 Parent(s): e2a8ba0

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. hyperparameters.json +1 -1
  3. model.pt +2 -2
  4. replay.mp4 +0 -0
  5. results.json +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - custom-implementation
7
  - deep-rl-class
8
  model-index:
9
- - name: reinforce-pixelcopter
10
  results:
11
  - task:
12
  type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
16
  type: Pixelcopter-PLE-v0
17
  metrics:
18
  - type: mean_reward
19
- value: 30.10 +/- 30.40
20
  name: mean_reward
21
  verified: false
22
  ---
 
6
  - custom-implementation
7
  - deep-rl-class
8
  model-index:
9
+ - name: Reinforce-pixelcopter
10
  results:
11
  - task:
12
  type: reinforcement-learning
 
16
  type: Pixelcopter-PLE-v0
17
  metrics:
18
  - type: mean_reward
19
+ value: -2.70 +/- 0.46
20
  name: mean_reward
21
  verified: false
22
  ---
hyperparameters.json CHANGED
@@ -1 +1 @@
1
- {"h_size": 64, "n_training_episodes": 25000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.8, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
 
1
+ {"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dae2b361c633994d337b236915c64ac011592aafbd3bfcfc16c07f295f9697c0
3
- size 39175
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37da35638660243a1aa62b21b590e64dd7e3b5b3f46769aab12d92864e6a27ea
3
+ size 2963
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 30.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-19T17:33:20.346493"}
 
1
+ {"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-19T17:36:56.576071"}