PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)

BabyAI platform. A testbed for training agents to understand and execute language commands.

Code for the paper "Meta-Learning Shared Hierarchies"

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Playing Pokemon Red with Reinforcement Learning

A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.

Imitation learning algorithms

Gym environment for building simulation and control using reinforcement learning

Partially Observable Process Gym

Official reinforcement learning environment for demand response and load shaping

This repository contains implementations and illustrative code to accompany DeepMind publications

Generative Agents: Interactive Simulacra of Human Behavior

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Source Code for A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

Benchmarking the Spectrum of Agent Capabilities

A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges

A suite of test scenarios for multi-agent reinforcement learning.

Simplifying reinforcement learning for complex game environments

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"

A curated list of reinforcement learning with human feedback resources (continually updated)

Train transformer language models with reinforcement learning.

Aggregate multiple tensorboard runs to new summary or csv files

Massively parallel rigidbody physics simulation on accelerator hardware.

A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch

2024 up-to-date list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.

Textbook on reinforcement learning from human feedback

Official code repo for the MARL book (www.marl-book.com)

AllenAI's post-training codebase