Clean baseline implementation of PPO using an episodic TransformerXL memory

Baseline implementation of recurrent PPO using truncated BPTT

[ 👾 ] ➡️ 💾 ➡️ { 🎮🕹️ } Extra Stable-Baselines3 buffer classes. Reducing RL memory usage drastically with minimal overhead.

Deep Reinforcement Learning by using Truly Proximal Policy Optimization in Tensorflow 2 and Pytorch

Deep Reinforcement Learning by using an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO)

Monte Carlo Search Tree for training shared Actor-Critic-Network on the game Hex🏋️

PyTorch implementation of V-MPO

Reinforcement Learning Tutorial (强化学习教程)

This repository contains all of the Reinforcement Learning-related projects I've worked on. The projects are part of the graduate course at the University of Tehran.

Reinforcement learning, Policy Gradient, Actor-Critic, AC, Agent-based Simulation, Simple-world

This repository contains the implementation of a wide variety of Reinforcement Learning Projects in different applications of Bandit Algorithms, MDPs, Distributed RL and Deep RL. These projects include university projects and projects implemented due to interest in Reinforcement Learning.

Autonomous Parking with Deep Reinforcement Learning Custom MDP Development

Stock Portfolio Management using tabular and deep Q-learning methods - extension of FinRL repo

Repository containing basic algorithm applied in python.

My content of CS294 Deep Reinforcement Learning course, conduced by Sergey Levine from UC Berkeley.

Containing a custom-built Reinforcement Learning environment and implementations of key RL algorithms like Q-learning and SARSA, tested in scenarios such as a drone navigation challenge and the Frozen Lake environment.

On-policy MCTS combined with deep learning to train an actor-critic neural network that plays Hex (Con-tac-tix).

🧗Comparative Reinforcement Learning analysis implementing SARSA (On-Policy) vs Q-Learning (Off-Policy) from scratch on OpenAI Gymnasium CliffWalking-v1 with live side-by-side animations and policy heatmaps.

A minimal, from-scratch implementation of SARSA (on-policy, model-free RL) on a custom GridWorld with no external RL libraries. Emphasizes algorithmic clarity and correct temporal dynamics for understanding model-free control from first principles.

Applying Deep Reinforcement Learning for Gridworld Best-Route Navigation