PyTorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

Official Github Repository for "Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints". (NeurIPS 2023)

Hands-on Deep Reinforcement Learning, published by Packt

PyTorch implementation of FQF, IQN and QR-DQN.

PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Du…

A PyTorch implementation of "WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning"

Robust and safe deep reinforcement learning algorithms

Official implementation for "Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk" (IJCAI 2022)

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

Code for the paper "WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning"

[NeurIPS2023] Official code of "Understanding Contrastive Learning via Distributionally Robust Optimization"

This study is using distributionally robust optimization (DRO) algorithm with conditional value-at-risk (CVaR) to solve self-scheduling problem to obtain a suitable and adjustable self-scheduling s…

PyTorch implementation of Constrained Reinforcement Learning for Soft Actor Critic Algorithm

Deep Learning (FS 2020)

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

Value-Decomposition Multi-Agent Actor-Critics

We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enhanced algorithm achieves 100% win rates on SMAC-V1 and superi…

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

MessySMAC - A Modified StarCraft MultiAgent Challenge with Configurable State Uncertainty

This is the official implementation of ERL-Re2.

Research Papers and Code Repository on the Integration of Evolutionary Algorithms and Reinforcement Learning

(ICML 2023) The official code for RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework

Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space

Robust Multi-Agent Reinforcement Learning with State Uncertainty

Lightweight version of MAPPO to help you quickly migrate to your local environment.