Memory-like Adaptive Modeling Multi-Agent Learning System

SUMMARY In this work, we propose a self-supervised multi-agent system, termed a memory-like adaptive modeling multi-agent learning system (MAMMALS), that realizes online learning towards behavioral pattern clustering tasks for time series. Encoding the visual behaviors as discrete timeseries(DTS),andtrainingandmodelingtheminthemulti-agentsystemwithabio-memory-likeform.Wefinallyimplementedafullydecentralized multi-agentsystemdesignframeworkandcompleteditsfeasibilityverifica- tion in a surveillance video application scenario on vehicle path clustering. In multi-agent learning, using learning methods designed for individual agents will typically perform poorly globally because of the behavior of ignoring the synergy between agents.

[1]  K. Czarnecki,et al.  SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving , 2022, CoRL.

[2]  Shimon Whiteson,et al.  Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning , 2019, Autonomous Agents and Multi-Agent Systems.

[3]  Klaus Diepold,et al.  Multi-agent deep reinforcement learning: a survey , 2021, Artificial Intelligence Review.

[4]  B. McNaughton,et al.  Neurons learn by predicting future activity , 2020, bioRxiv.

[5]  Zihan Zhou,et al.  Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning , 2020, ICLR.

[6]  H. Zha,et al.  Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery , 2019, AAMAS.

[7]  Yehia Abd Alrahman,et al.  Reconfigurable Interaction for MAS Modelling , 2019, AAMAS.

[8]  Matthew E. Taylor,et al.  A survey and critique of multiagent deep reinforcement learning , 2019, Autonomous Agents and Multi-Agent Systems.

[9]  Fei Sha,et al.  Actor-Attention-Critic for Multi-Agent Reinforcement Learning , 2018, ICML.

[10]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[11]  Shimon Whiteson,et al.  QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning , 2018, ICML.

[12]  Guy Lever,et al.  Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward , 2018, AAMAS.

[13]  Shimon Whiteson,et al.  Counterfactual Multi-Agent Policy Gradients , 2017, AAAI.

[14]  Sergey Levine,et al.  Time-Contrastive Networks: Self-Supervised Learning from Video , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Michael Wooldridge,et al.  From model checking to equilibrium checking: Reactive modules for rational verification , 2016, Artif. Intell..

[16]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[17]  Yadong Wang,et al.  LAMSA: fast split read alignment with long approximate matches , 2017, Bioinform..

[18]  Frans A. Oliehoek,et al.  Coordinated Deep Reinforcement Learners for Traffic Light Control , 2016 .

[19]  Alessio Lomuscio,et al.  MCMAS: an open-source model checker for the verification of multi-agent systems , 2017, International Journal on Software Tools for Technology Transfer.

[20]  Alexei A. Efros,et al.  Unsupervised Visual Representation Learning by Context Prediction , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Michael Wooldridge,et al.  Iterated Boolean games , 2013, Inf. Comput..

[22]  Ronen I. Brafman,et al.  On the complexity of planning for agent teams and its implications for single agent planning , 2013, Artif. Intell..

[23]  Dejan Nickovic,et al.  Dynamic Reactive Modules , 2011, CONCUR.

[24]  Bart De Schutter,et al.  A Comprehensive Survey of Multiagent Reinforcement Learning , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[25]  Bart De Schutter,et al.  Multi-Agent Reinforcement Learning: A Survey , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[26]  Jing Liu,et al.  A multiagent evolutionary algorithm for constraint satisfaction problems , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[27]  Paul Harrenstein.  Logical Consequence and the Theory of Games , 2004 .

[28]  Thomas A. Henzinger,et al.  MOCHA: Modularity in Model Checking , 1998, CAV.

[29]  Thomas A. Henzinger,et al.  Reactive Modules , 1996, Proceedings 11th Annual IEEE Symposium on Logic in Computer Science.