carlosmirandad commited on
Commit
e7ce917
1 Parent(s): 0a2e492

Upload . with huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. hyperparameters.json +1 -1
  3. model.pt +1 -1
  4. replay.mp4 +0 -0
  5. results.json +1 -1
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  type: CartPole-v1
17
  metrics:
18
  - type: mean_reward
19
- value: 116.10 +/- 6.25
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
- # **Reinforce** Agent playing **CartPole-v1**
25
- This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
26
- To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
27
-
 
16
  type: CartPole-v1
17
  metrics:
18
  - type: mean_reward
19
+ value: 500.00 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
+ # **Reinforce** Agent playing **CartPole-v1**
25
+ This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
26
+ To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
27
+
hyperparameters.json CHANGED
@@ -1 +1 @@
1
- {"h_size": 16, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
 
1
+ {"h_size": 16, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:245cc14980530df295cb8d32d9472a8c8f032b3ad32439d5570c4629b52004aa
3
  size 2579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f21a9cc2f7c0cca9dd831f68c595a42832337867537445c93a9a047ed320c14
3
  size 2579
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "CartPole-v1", "mean_reward": 116.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-02T08:32:22.084724"}
 
1
+ {"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-03T23:31:11.057887"}