/Reinforcement-learning-agent

Repository with all the projects I have made this year

Primary LanguageJupyter Notebook

Reinforcement-learning-agent

This repository contains a collection of different reinforcement learning projects, each implementing RL agent.

Each directory in this repository represents a distinct project, with its own agent and corresponding infrastructure. I have designed and implemented each of these projects.

Projects

  • Actor-Critic: Implements an Actor-Critic reinforcement learning agent.
  • DQN-experience-replay: Implements a Deep Q-Network (DQN) agent with experience replay.
  • DynaQ-Qlearning: Implements a combination of Dyna-Q and Q-Learning.
  • PPOKL: Implements a Proximal Policy Optimization (PPO) agent using Kullback-Leibler (KL) divergence.
  • Rld: An older project implementing a unique reinforcement learning agent.
  • TME1env: Contains an environment and corresponding agent for teaching purposes.
  • ddpg: Implements a Deep Deterministic Policy Gradient (DDPG) agent.
  • dqn-igs-her: Implements a DQN agent using Importance Sampling (IS) and Hindsight Experience Replay (HER).
  • gail: Implements a Generative Adversarial Imitation Learning (GAIL) agent.
  • gan: Implements a Generative Adversarial Network (GAN) agent.
  • gridworld-random-agent: Implements a random agent in a Gridworld environment.
  • multi-agent: Contains a multi-agent reinforcement learning project.
  • variational-encoder: Implements a reinforcement learning agent with a Variational Autoencoder (VAE).

Feel free to explore each project's individual directory for more information about its structure and agent.

Note: .DS_Store is a system file used by the macOS operating system and does not contain any project-related content.