Upload . with huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+- CartPole-v1
+model-index:
+- name: Reinforce_CartPole-v1
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 495.68 +/- 36.23
+      name: mean_reward
+      verified: false
+---
+
+  # **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
+  

hyperparameters.json

@@ -0,0 +1 @@
+{"experiment_name": "Reinforce_CartPole-v1", "device": "gpu", "policy": {"_target_": "lib.reinforce.Policy", "h_size": 32}, "optimizer": {"_target_": "torch.optim.Adam", "lr": 0.001}, "train_hparams": {"n_training_episodes": 5000, "max_steps": 1000, "gamma": 1.0, "print_every": 100}, "eval_hparams": {"n_eval_episodes": 1000, "max_steps": 1000}, "model_path": "model.pt", "hparams_path": "hyperparameters.json", "video_path": "replay.mp4", "video_fps": 30, "train_env": {"_target_": "gym.make", "id": "CartPole-v1", "render_mode": "rgb_array"}, "eval_env": {"_target_": "gym.make", "id": "CartPole-v1", "render_mode": "rgb_array"}}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bc8847e0459581890794c1ace0efbcba4160a7ff57d845fcb87cf1cd9d7f2f
+size 3475

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 495.678, "std_reward": 36.22690044704349, "n_eval_episodes": 1000, "eval_datetime": "2023-01-08T19:35:11.787246"}