New Zealand


Peer incentivation (PI) is a recent approach, where all agents learn to reward or to penalize each other which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly integrated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information which limits scalability and applicability to real-world scenarios, where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to mutually exchange acknowledgment tokens to shape individual rewards. Each agent evaluates the monotonic improvement of its individual situation in order to accept or reject acknowledgment requests from other agents. MATE is a completely decentralized approach which only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can defect from the protocol and where communication failures can occur.

AAMAS 2022

Emergent Cooperation from Mutual Acknowledgment Exchange

emergent cooperation

peer incentivization

mutual acknowledgments

multi-agent learning

reinforcement learning

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

The AAMAS conference series was initiated in 2002 in Bologna, Italy as a joint event comprising the 6th International Conference on Autonomous Agents (AA), the 5th International Conference on Multiagent Systems (ICMAS), and the 9th International Workshop on Agent Theories, Architectures, and Languages (ATAL).

Subsequent AAMAS conferences have been held in Melbourne, Australia (July 2003), New York City, NY, USA (July 2004), Utrecht, The Netherlands (July 2005), Hakodate, Japan (May 2006), Honolulu, Hawaii, USA (May 2007), Estoril, Portugal (May 2008), Budapest, Hungary (May 2009), Toronto, Canada (May 2010), Taipei, Taiwan (May 2011), Valencia, Spain (June 2012), Minnesota, USA (May 2013), Paris, France (May 2014), Istanbul, Turkey (May 2015), Singapore (May 2016), São Paulo (2017) and Stockholm, Sweden (2018), Montreal (May 2019), Auckland (May 2020, Virtual), London (May 2021, Virtual).
<br>
<br>



A ticket is required to attend this event, please register using the link below:

https://aamas2022-conference.auckland.ac.nz/attending/registration/

Registration Is Required

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

technical paper


In the house allocation problem with lower and upper quotas, we are given a set of applicants and a set of projects. Each applicant has a strictly ordered preference list over the projects, while the projects are equipped with a lower and an upper quota. A feasible matching assigns the applicants to the projects in such a way that a project is either matched to no applicant or to a number of applicants between its lower and upper quota. 
In this model we study two classic optimality concepts: Pareto optimality and popularity. We show that finding a popular matching is hard even if the maximum lower quota is 2 and that finding a perfect Pareto optimal matching, verifying Pareto optimality, and verifying popularity are all NP-complete even if the maximum lower quota is 3. We complement the last three negative results by showing that the problems become polynomial-time solvable when the maximum lower quota is 2, thereby answering two open questions of Cechlárová and Fleiner. Finally, we also study the parameterized complexity of all four mentioned problems.

Pareto optimal and popular house allocation with lower and upper quotas


Weighted voting games are typically used to model situations where a number of agents vote against or for a proposal. In such games, a proposal is accepted if a weighted sum of the votes exceeds a specified threshold. As the influence of a player over the outcome is not in general proportional to her assigned weight, various power indices have been proposed to measure each player's influence. The inverse power index problem is the problem of designing a weighted voting game that achieves a set of desirable influences as they are measured by a predefined power index. Recent work has shown that exactly solving the inverse power index problem is computationally intractable when the power index is in the class of semivalues --- a broad class that includes the popular Shapley value and Banzhaf index. In this work, we design efficient approximation algorithms for the inverse semivalue problem. We develop a unified methodology that leads to computationally efficient algorithms that solve the inverse semivalue problem to any desired accuracy. We perform an extensive experimental evaluation of our algorithms on both synthetic and real inputs. Our experiments show that our algorithms are scalable and achieve higher accuracy compared to previous methods in the literature.

Efficient Approximation Algorithms for the Inverse Semivalue Problem


Deep reinforcement learning (RL) has recently shown great promise in robotic continuous control tasks. Nevertheless, prior research in this vein center around the centralized learning setting that largely relies on the communication availability among all the components of a robot. However, agents in the real world often operate in a decentralised fashion without communication due to latency requirements, limited power budgets and safety concerns. By formulating robotic components as a system of decentralised agents, this work presents a decentralised multiagent reinforcement learning framework for continuous control. To this end, we first develop a cooperative multiagent PPO framework that allows for centralized optimisation during training and decentralised operation during execution. However, the system only receives a global reward signal which is not attributed towards each agent. To address this challenge, we further propose a generic game-theoretic credit assignment framework which computes agent-specific reward signals. Last but not least, we also incorporate a model-based RL module into our credit assignment framework, which leads to significant improvement in sample efficiency. We demonstrate the effectiveness of our framework on experimental results on Mujoco locomotion control tasks.

Multiagent Model-based Credit Assignment for Continuous Control


To deal with the underlying heterogeneous law enforcement problem
(LEPH), one needs to allocate police officers to dynamic tasks whose
locations, arrival times, and importance levels are unknown a priory.
Addressing this challenge and inspired by real police logs, this
research aims to solve the LEPH problem by using and comparing
three methods: Fisher market-based FMC_TAH+, swarm intelligence
HDBA, and Simulated Annealing SA algorithms. The three methods
were compared in this study for the performance measures that
are commonly used by law enforcement authorities. The results
indicate an advantage for FMC_TAH+ both in total utility and in the
average arrival time to tasks. Also, compared respectively to HDBA
and SA, FMC_TAH+ leads to 34% and 32% higher team utility in the
highest shift workload.

Towards addressing dynamic multi-agent task allocation in law enforcement


Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We propose Multi-Objective Reinforced Active Learning (MORAL), a novel method for combining diverse demonstrations of social norms into a Pareto optimal policy. Through maintaining a distribution over scalarization weights, our approach is able to interactively tune a deep RL agent towards a variety of preferences, while eliminating the need for computing multiple policies. We empirically demonstrate the effectiveness of MORAL in two scenarios, which model a delivery and an emergency task that require an agent to act in the presence of normative conflicts. Overall, we consider our research a step towards multi-objective RL with learned rewards, bridging the gap between current reward learning and machine ethics literature.

MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning


While reinforcement learning (RL) has made great advances by handling increasingly large data, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) provide a principled answer to both state estimation and the exploration-exploitation trade-off, but struggles to scale. To tackle this challenge, BRL frameworks with various modeling assumptions have been proposed, with varied success. This work first presents a representation-agnostic formulation of BRL in partially observable environments, unifying the previous models under one theoretical umbrella. To demonstrate its practical significance we also propose a novel derivation, based on dropout networks, called BADDr: Bayes-adaptive deep dropout RL\@. Under this parameterization, in contrast to previous work, the belief over the system's state and its dynamics is a more scalable inference problem. We solve the resulting problem with a Monte-Carlo tree search planner, and empirically show that our method is competitive with state-of-the-art BRL methods on small domains and is able to solve much larger ones.


BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs


Multi-agent reinforcement learning (MARL) is a promising framework for solving complex tasks with many agents. However, a key challenge in MARL is defining private utility functions that ensure coordination when training decentralized agents. This challenge is especially prevalent in unstructured tasks with sparse rewards and many agents. We show that successor features can help address this challenge by disentangling an individual agent's impact on the global value function from that of all other agents. We use this disentanglement to compactly represent private utilities that support stable training of decentralized agents in unstructured tasks. We implement our approach using a centralized training, decentralized execution architecture and test it in a variety of multi-agent environments. Our results show improved performance and training time relative to existing methods and suggest that disentanglement of successor features offers a promising approach to coordination in MARL.

Disentangling Successor Features for Coordination in Multi-agent Reinforcement Learning


Multi-Objective Reinforcement Learning (MORL) setup naturally arises in many places where an agent optimizes multiple objectives. We consider the problem of MORL where multiple objectives are combined using a non-linear scalarization. We combine the vector objectives with a concave scalarization function and maximize this scalar objective. To work with the non-linear scalarization, in this paper, we propose a solution using steady-state occupancy measures and long-term average rewards. We show that when the scalarization function is element-wise increasing, the optimal policy for the scalarization is also Pareto optimal. To maximize the scalarized objective, we propose a model-based posterior sampling algorithm that obtains a regret bound of $\Tilde{O}(KDS\sqrt{A/T})$ for $K$ objectives. Additionally, we propose policy-gradient and actor-critic algorithms for MORL. For the policy gradient actor, we obtain the gradient using chain rule, and we learn different critics for each of the $K$ objectives. Finally, we implement our algorithms on multiple environments including deep-sea treasure, and network scheduling setups to demonstrate that the proposed algorithms can optimize non-linear scalarization of multiple objectives.

Multi-Objective Reinforcement Learning with Non-Linear Scalarization

We examined principles of graded argumentation semantics (independence, anonymity, void precedence, and maximality) to explore if (a) they realistically model human reasoning, (b) graphical representation of arguments facilitates compliance with the principles, (c) there is a positive correlation between compliance with different principles, and (d) this compliance is related to cognitive reflection, need for cognition and faith in intuition. Our results indicate that there are major differences in the compliance with the several argumentation principles studied in this paper. However, compliance with argumentation principles was consistently better and more strongly correlated in the group presented with graphs. Moreover, cognitive reflection correlated with compliance to some principles, but only in the graph group.

Graphical Representation Enhances Human Compliance with Principles for Graded Argumentation Semantics


We propose Streaming Bandits, a Restless Multi-Armed Bandit(RMAB) framework in which heterogeneous arms may arrive and leave the system after staying on for a finite lifetime. Streaming Bandits naturally capture the health-intervention planning problem, where health workers must manage the health outcomes of a patient cohort while new patients join and existing patients leave the cohort each day. Our contributions are as follows: (1) We de-rive conditions under which our problem satisfies indexability, a pre-condition that guarantees the existence and asymptotic optimality of the Whittle Index solution for RMABs. We establish the conditions using a polytime reduction of the Streaming Banditsetup to regular RMABs. (2) We further prove a phenomenon that we call index decay — whereby the Whittle index values decrease for short residual lifetimes — driving the intuition underpinning our algorithm. (3) We propose a novel and efficient algorithm to compute the index-based solution for Streaming Bandits. Unlike previous methods, our algorithm does not rely on solving the costly finite horizon problem on each arm of the RMAB, thereby lowering the computational complexity compared to existing methods. (4) Finally, we evaluate our approach via simulations run on real-world data sets from a tuberculosis patient monitoring task and an intervention planning task for improving maternal healthcare, in addition to other synthetic domains. Across the board, our algorithm achieves a 2-orders-of-magnitude speed-up over existing methods while maintaining the same solution quality

Emergent Cooperation from Mutual Acknowledgment Exchange

Downloads

Next from AAMAS 2022

Pareto optimal and popular house allocation with lower and upper quotas

Similar lecture

SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning

Emergent Cooperation from Mutual Acknowledgment Exchange

.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 2022

Pareto optimal and popular house allocation with lower and upper quotas

Similar lecture

SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning

Downloads