Multiagent Decision Making and Learning in Urban Environments

Our increasingly interconnected urban environments provide several opportunities to deploy intelligent agents—from self-driving cars, ships to aerial drones—that promise to radically improve productivity and safety. Achieving coordination among agents in such urban settings presents several algorithmic challenges—ability to scale to thousands of agents, addressing uncertainty, and partial observability in the environment. In addition, accurate domain models need to be learned from data that is often noisy and available only at an aggregate level. In this paper, I will overview some of our recent contributions towards developing planning and reinforcement learning strategies to address several such challenges present in largescale urban multiagent systems.

[1]  Marc Toussaint,et al.  Probabilistic Inference Techniques for Scalable Multiagent Decision Making , 2015, J. Artif. Intell. Res..

[2]  Ilche Georgievski,et al.  International Conference on Automated Planning and Scheduling , 2013 .

[3]  Hoong Chuin Lau,et al.  Policy Gradient With Value Function Approximation For Collective Multiagent Planning , 2018, NIPS.

[4]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[5]  Hoong Chuin Lau,et al.  Collective Multiagent Sequential Decision Making Under Uncertainty , 2017, AAAI.

[6]  Tao Sun,et al.  Message Passing for Collective Graphical Models , 2015, ICML.

[7]  Felipe Meneguzzi.  Sixth International Joint Conference on Autonomous Agents and Multiagent Systems , 2008 .

[8]  C. Daganzo.  THE CELL TRANSMISSION MODEL.. , 1994 .

[9]  Alexander J. Smola,et al.  Neural Information Processing Systems , 1997, NIPS 1997.

[10]  Shlomo Zilberstein,et al.  Dual Formulations for Optimizing Dec-POMDP Controllers , 2016, ICAPS.

[11]  Tomoharu Iwata,et al.  Neural Collective Graphical Models for Estimating Spatio-Temporal Population Flow from Aggregated Data , 2019, AAAI.

[12]  Biplav Srivastava,et al.  Collective Diffusion Over Networks: Models and Inference , 2013, UAI.

[13]  Makoto Yokoo,et al.  Networked Distributed POMDPs: A Synergy of Distributed Constraint Optimization and POMDPs , 2005, IJCAI.

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

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

[16]  Hoong Chuin Lau,et al.  Multiagent Decision Making For Maritime Traffic Management , 2019, AAAI.

[17]  Supriyo Ghosh,et al.  Probabilistic Inference Based Message-Passing for Resource Constrained DCOPs , 2015, IJCAI.

[18]  Hoong Chuin Lau,et al.  Credit Assignment For Collective Multiagent RL With Global Rewards , 2018, NeurIPS.

[19]  Shun Zhang,et al.  Autonomous Intersection Management for Semi-Autonomous Vehicles , 2015 .

[20]  David A. Freedman,et al.  De Finetti's generalizations of exchangeability , 1980 .

[21]  Michael Wooldridge,et al.  Autonomous agents and multi-agent systems , 2014 .

[22]  Guy Van den Broeck,et al.  Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference , 2014, AAAI.

[23]  Marco Aiello,et al.  AAAI Conference on Artificial Intelligence , 2011, AAAI Conference on Artificial Intelligence.

[24]  Robert M Thrall,et al.  Mathematics of Operations Research. , 1978 .

[25]  Thomas G. Dietterich,et al.  Approximate Inference in Collective Graphical Models , 2013, ICML.