This repository contains an implementation of the Deep Deterministic Policy Gradient (DDPG) algorithm to solve the MountainCarContinuous-v0 environment from OpenAI Gym.
The aim of this project is to demonstrate how DDPG, an actor-critic, model-free algorithm based on deep reinforcement learning, can be applied to classic continuous control tasks like MountainCarContinuous-v0.
- DDPG implementation using PyTorch (or TensorFlow if you used it).
- Continuous action space policy for effective control of the car.
- Script for training and evaluation.
- Configurable hyperparameters.
- Python 3.6+
- numpy
- gym (or gymnasium)
- torch (if using PyTorch)
- matplotlib (for plotting, optional)