#
anle2017
Follow
Starred repositories
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)
[AAAI2024] A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning
[TNNLS] Imitative Expert Prior-Guided Reinforcement Learning for Autonomous Driving
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
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…
A collection of recent MARL papers
PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
Source files to replicate experiments in my ICLR 2022 paper.
Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Air Combat
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
Official PyTorch code for "Recurrent Off-policy Baselines for Memory-based Continuous Control" (DeepRL Workshop, NeurIPS 21)
A collection of MARL benchmarks based on TorchRL
Official implementation of HARL algorithms based on PyTorch.
Code for the paper "Meta-Learning Shared Hierarchies"
Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation. Project website: http://himos.cs.uni-freiburg.de
A library for training robots using RL under the scheme of multi-level RL.
A repository of high-performing hierarchical reinforcement learning models and algorithms.
This repository is created for my thesis during the bachelor degree at Innopolis University. The topic for research is Learning behavioral strategies for a multi-robot system in a predator-prey env…
Clean implementation of Multi-Agent Reinforcement Learning methods (MADDPG, MATD3, MASAC, MAD4PG) in TensorFlow 2.x
Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022
Connect Four Environment is a project designed for training reinforcement learning models to play the classic Connect4 game. It's compatible with OpenAI Gym / Gymnasium, includes a variety of bots,…
