Kunikazu Kobayashi, Koji Nakano, Takashi Kuremoto and Masanao Obayashi (February 1st 2010). Objective-based Reinforcement Learning System for Cooperative Behavior Acquisition, Application of Machine Learning, Yagang Zhang, IntechOpen, DOI: 10.5772/8615. 

Yoshiyuki Tajima and Takehisa Onisawa (February 1st 2010). Model-based Reinforcement Learning with Model Error and Its Application, Application of Machine Learning, Yagang Zhang, IntechOpen, DOI: 10.5772/8607. 

Daniela P. Alves, Li Weigang and Bueno B. Souza (January 1st 2008). Reinforcement Learning to Support Meta-Level Control in Air Traffic Management, Reinforcement Learning, Cornelius Weber, Mark Elshaw and Norbert Michael Mayer, IntechOpen, DOI: 10.5772/5293.

New Zealand

The presentation video of the paper &quot;META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation&quot; for AAMAS 2020.

AAMAS 2020

META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


AAAI 2023

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

The presentation video of the paper "META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation" for AAMAS 2020.

technical paper

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

Candidate Selections with Proportional Fairness Constraints

We consider an online resource allocation problem where tasks with specific values, sizes and resource requirements arrive dynamically over time, and have to be either serviced or rejected immediately. Reinforcement learning is a promising approach for this, but existing work on reinforcement learning has neglected that task owners may misreport their task requirements or values strategically when this is to their benefit. To address this, we apply mechanism design and propose a novel mechanism based on reinforcement learning that aims to maximise social welfare, is strategyproof and individually rational (i.e., truthful reporting and participation are incentivised). In experiments, we show that our algorithm achieves results that are typically within 90% of the optimal social welfare, while outperforming approaches that use fixed pricing (by up to 86% in specific cases).

Strategyproof Reinforcement Learning for Online Resource Allocation

In this work, we formalize and study the Moving Agents in Formation (MAiF) problem, that combines the tasks of finding short collision-free paths for multiple agents and keeping them in close adherence to a desired formation while they are moving. We develop a two-phase search algorithm, called SWARM-MAPF, whose first phase is inspired by swarm-based algorithms (in open regions) and whose second phase is inspired by multi-agent path-finding (MAPF) algorithms (in congested regions). In the first phase, SWARM-MAPF selects a leader among the agents and finds a path for it that is sufficiently far away from the obstacles so that the other agents can preserve the desired formation around it. It also identifies the critical segments of the leader's path where the other agents cannot preserve the desired formation and the refinement of which has thus to be delegated to the second phase. In the second phase, SWARM-MAPF refines these segments. Theoretically, we prove that SWARM-MAPF is complete. Empirically, we show that SWARM-MAPF scales well and is able to find close-to-optimal solutions.

Moving Agents in Formation in Congested Environments

Evolutionary optimization is a generic population-based metaheuristic that can be adapted to solve a wide variety of optimization problems and has proven very effective for combinatorial optimization problems. However, the potential of this metaheuristic has not been utilized in Distributed Constraint Optimization Problems (DCOPs), a well-known class of combinatorial optimization problems prevalent in Multi-Agent Systems. In this paper, we present a novel population-based algorithm, Anytime Evolutionary DCOP (AED), that uses evolutionary optimization to solve DCOPs. In AED, the agents cooperatively construct an initial set of random solutions and gradually improve them through a new mechanism that considers an optimistic approximation of local benefits. Moreover, we present a new anytime update mechanism for AED that identifies the best among a distributed set of candidate solutions and notifies all the agents when a new best is found. In our theoretical analysis, we prove that AED is anytime. Finally, we present empirical results indicating AED outperforms the state-of-the-art DCOP algorithms in terms of solution quality.

An Anytime Evolutionary DCOP Algorithm

Playing Games in the Dark: An approach for cross-modality transfer in reinforcements learning

Rationals vs Byzantine Players in Committee-Based Blockchains

Toward enabling next-generation robots capable of socially intelligent interaction with humans, we present a computational model of interactions in a social environment of multiple agents and multiple groups. The Multiagent Group Perception and Interaction (MGpi) network is a deep neural network that predicts the appropriate social action to execute in a group conversation (e.g., speak, listen, respond, leave), taking into account neighbors' observable features (e.g., location of people, gaze orientation, distraction, etc.). A central component of MGpi is the Kinesic-Proxemic-Message (KPM) gate, that performs social signal gating to extract important information from a group conversation. In particular, KPM gate filters incoming social cues from nearby agents by observing their body gestures (kinesics) and spatial behavior (proxemics). The MGpi network and its KPM gate are learned via imitation learning, using demonstrations from our designed social interaction simulator. Further, we demonstrate the efficacy of the KPM gate as a social attention mechanism, achieving state-of-the-art performance on the task of group identification without using explicit group annotations, layout assumptions, or manually chosen parameters.

MGpi: A Computational Model of Multiagent Group Perception and Interaction

Multi Agent Path Finding (MAPF) is the problem of planning paths for agents to reach their targets from their start locations, such that the agents do not collide while executing the plan. In safety-critical systems, the plan is typically checked by a human supervisor, who decides on whether to allow its execution. In such cases, we wish to convince the human that the plan is indeed collision free. To this end, we propose an \emph{explanation scheme} for MAPF, which bases explanations on simplicity of visual verification by human's cognitive process. The scheme decomposes a plan into segments such that within each segment, the paths of the agents are disjoint. Then, we can convince the supervisor that the plan is collision free using a small number of images (dubbed an \emph{explanation}). In addition, we can measure the simplicity of a plan by the number of segments required for the decomposition. We study the complexity of algorithmic problems that arise by the explanation scheme, as well as the tradeoff between the length (makespan) of a plan and its minimal decomposition. We also provide experimental results of our scheme both in a continuous and in a discrete setting.

Explainable Multi Agent Path Finding

Emergency Response Management (ERM) is a critical problem faced by communities across the globe. Despite this, it is common for ERM systems to follow myopic decision policies in the real world. Principled approaches to aid ERM decision-making under uncertainty have been explored but have failed to be accepted into real systems. We identify a key issue impeding their adoption --- algorithmic approaches to emergency response focus on reactive, post-incident dispatching actions, i.e. optimally dispatching a responder \textit{after} incidents occur. However, the critical nature of emergency response dictates that when an incident occurs, first responders always dispatch the closest available responder to the incident. We argue that the crucial period of planning for ERM systems is not post-incident, but between incidents. This is not a trivial planning problem --- a major challenge with dynamically balancing the spatial distribution of responders is the complexity of the problem. An orthogonal problem in ERM systems is planning under limited communication, which is particularly important in disaster scenarios that affect communication networks. We address both problems by proposing two partially decentralized multi-agent planning algorithms that utilize heuristics and exploit the structure of the dispatch problem. We evaluate our proposed approach using real-world data, and find that in several contexts, dynamic re-balancing the spatial distribution of emergency responders reduces both the average response time as well as its variance.

On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities

Timely evacuation is a standard recommendation by local agencies before disaster events such as hurricanes, which have enough advance notice. However, it has been observed in many recent disasters (e.g., Sandy), that only a small fraction of the population evacuates in time. Recent work by social scientists has examined the factors that influence household evacuation decisions; in addition to individual factors it has been found that peer effect plays a role in this decision but in two opposing ways. Specifically, households are motivated to evacuate if their neighbors evacuate. However, if too many neighbors leave then some households have concerns of looting and crime, and they choose not to evacuate. This makes the dynamics of evacuation very complex. In this paper, we use a detailed agent based model to study the dynamics of evacuation in Virginia's coastal region. We use data from a large survey and social contagion and collective action theories to develop the model. We evaluate different strategies to increase evacuation.

META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation

Downloads

Next from AAMAS 2020

Candidate Selections with Proportional Fairness Constraints

Similar lecture

SKDBERT: Compressing BERT via Stochastic Knowledge Distillation

META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2020

Candidate Selections with Proportional Fairness Constraints

Similar lecture

SKDBERT: Compressing BERT via Stochastic Knowledge Distillation

Downloads