Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 100000.00 +/- 0.00
+      value: 120000.00 +/- 0.00
       name: mean_reward
       verified: false
 ---
@@ -24,8 +24,4 @@ model-index:
   # **Reinforce** Agent playing **CartPole-v1**
   This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
   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
-
-  Some notes: I used gymnasium and not gym, so I had to modify some instructions to make the page work. I trained the agent for 2000 episodes and I achieved a model that never makes the pole fall!!!
-
-  The final score is 100000 only because I let the scoring function evaluate a maximum of 100000 steps ... but the score could be +infinity if I let the game going on forever!!!
   

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 1000, "max_eval": 120000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2709fa1fedf430353c54e84ffb6ec3c5e6a78b1b8c9b20ff80d9014c432a2d
-size 3392
+oid sha256:e4f2cb643426336ef544d9d061a762a5265aa29a7450c66a6db6dac2a0c67b5c
+size 3264

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 100000.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-16T23:26:12.397339"}
+{"env_id": "CartPole-v1", "mean_reward": 120000.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-17T10:27:28.884752"}