CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

DrQ: Data regularized Q

RAD: Reinforcement Learning with Augmented Data

⚡ Flashbax: Accelerated Replay Buffers in JAX

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

ExORL: Exploratory Data for Offline Reinforcement Learning

Official PyTorch code for "Recurrent Off-policy Baselines for Memory-based Continuous Control" (DeepRL Workshop, NeurIPS 21)

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

Actor Prioritized Experience Replay

solving a simple 4*4 Gridworld almost similar to openAI gym FrozenLake using Qlearning Temporal difference method Reinforcement Learning

off-policy algorithm utilizing offline and online data

RosefinAIEngine of Rosfintech

TensorFlow implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"

PyTorch implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"

Off-Policy Correction for Actor-Critic Algorithms in Deep Reinforcement Learning

DDPG and D4PG Continuous Control

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.

Collection of codes pertaining to my research in model-free RL algorithms.

A novel method to incorporate existing policy (Rule-based control) with Reinforcement Learning.