zeynpakn/Reinforce-CartPole-v1

Reinforce Agent playing CartPole-v1

This is a trained model of a Reinforce agent playing CartPole-v1, implemented from scratch in PyTorch. 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

Evaluation

Episodes	Mean reward	Std reward	Mean − Std
10	500.00	0.00	500.00

Hyperparameters

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

Usage

import torch
# The Policy class from the training notebook must be defined before loading
model = torch.load("model.pt", weights_only=False)