beaulolve Goto Github PK

pymarl3

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 superior performance on SMAC-V2.

pymarl_transformers

Official repository of the paper TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems (AAMAS 2023)

pyro_agents

Agent models implemented with Pyro

pythonrobotics

Python sample codes for robotics algorithms.

pytorch-vqvae

Vector Quantized VAEs - PyTorch Implementation

qatten

qdpp

Multi-Agent Determinantal Q-Learning

qpd

This is the code for Q-value Path Decomposition for Deep Multiagent Reinforcement Learning (NeurIPS 2019).

quadrotorfly

This is a dynamic simulation for quadrotor UAV

qvmix

Repositery for the paper "QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning"

race

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

resq

The source code of "ResQ: A Residual Q Function-based Approach for Multi-Agent Reinforcement Learning Value Factorization. NeurIPS 2022"

revisiting_marl

Official codebase for paper "Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning" (ICML22)

riskq

rl-based-event-triggered-mpc

rl-path-racing

We are trying to combine reinforcement learning and trajectory optimization to win in F 1/10 racing.

rl-spf

a representation learning method that predicts the Fourier transform of state sequences to improve sample efficiency of RL algorithms.

rl-state_mask

rl_ardrone

Autonomous Navigation of UAV using Reinforcement Learning algorithms.

rlbeyondbellman

Code supporting my 2020 conference presentation "Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution" with Madhavun Candadai and Eduardo J. Izquierdo.

rmix

robust_cbf

rode

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523)

rope

Code for State-Action Similarity-Based Representations for Off-Policy Evaluation (NeurIPS 2023).

ros-tcp-connector

ros_unity_sensor_suite

Provide a unified sensor suite in Unity3d for ROS

rspo-iclr-2022

The official code repository for "Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization".

s-mixup

The official source code for "S-Mixup: Structural Mixup for Graph Neural Networks", accepted at CIKM 2023 (Short Paper).

sacha

safe-control-gym

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL