MARL-basics.md

Paper Collection of MARL

Contributors:

MARL Basic

CTDE : Centralized Training, Decentralized Execution

1. VDN :Value-decomposition networks for cooperative multi-agent learning, Sunehag P, et al 2017.
2. QMIX : Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning Rashid T, et al 2018, ICML
3. QTRAN : Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning Son K, et al 2019, ICML
4. QATTEN : Qatten: A general framework for cooperative multiagent reinforcement learning Yang Y, et al 2020.
5. MADDPG : Multi-agent actor-critic for mixed cooperative-competitive environments Lowe R et al 2017, NIPS
6. COMA : Counterfactual multi-agent policy gradients Foerster J et al 2018, AAAI
7. MAPPO : Joint optimization of handover control and power allocation based on multi-agent deep reinforcement learning Guo D, et al 2020
8. HATRPO & HAPPO : Trust region policy optimisation in multi-agent reinforcement learning Kuba J G, et al 2021
9. MA3C : Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning Xiao Y, et al 2022

DTDE : Decentralized Training, Decentralized Execution

IPPO : Is independent learning all you need in the starcraft multi-agent challenge? de Witt C S, et al 2020

Communication

1. RIAL & DIAL: Learning to communicate with deep multi-agent reinforcement learning Foerster J, et al 2016, NIPS
2. CommNet : Learning multiagent communication with backpropagation Sukhbaatar S, et al 2016, NIPS
3. BicNet : Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games Peng P, et al 2017.
4. ATOC : Learning attentional communication for multi-agent cooperation Jiang J, et al 2018, NIPS
5. IC3Net : Learning when to communicate at scale in multiagent cooperative and competitive tasks Singh A, et al 2018
6. Tramac : Tarmac: Targeted multi-agent communication Das A, et al 2019, ICML
7. NDQ : Learning nearly decomposable value functions via communication minimization Wang T, et al 2019
8. SchedNet : Learning to schedule communication in multi-agent reinforcement learning Kim D, et al 2019
9. Social influence as intrinsic motivation for multi-agent deep reinforcement learning Jaques N, et al 2019, ICML
10. Infobot : Infobot: Transfer and exploration via the information bottleneck Goyal A, et al 2019

MARL FOR MAPF

1. PRMIAL : Primal: Pathfinding via reinforcement and imitation multi-agent learning Sartoretti G, et al 2019, ICRA
2. MARLSP : Learning to cooperate: Application of deep reinforcement learning for online AGV path finding Zhang Y, et al 2020, AAMAS
3. MAPPER: Mapper: Multi-agent path planning with evolutionary reinforcement learning in mixed dynamic environments Liu Z, et a 2020, IROS
4. G2RL : Mobile robot path planning in dynamic environments through globally guided reinforcement learning Wang B, et al 2020
5. PRMIAL2 : PRIMAL2: Pathfinding via reinforcement and imitation multi-agent learning-lifelong Damani M, et al 2021, ICRA
6. DHC :Distributed heuristic multi-agent path finding with communication Ma Z, et al 2021, ICRA
7. PICO : Multi-Agent Path Finding with Prioritized Communication Learning Li W, et al 2022