New Zealand

Toshihiko Watanabe (February 1st 2010). Hierarchical Reinforcement Learning Using a Modular Fuzzy Model for Multi-Agent Problem, New Advances in Machine Learning, Yagang Zhang, IntechOpen, DOI: 10.5772/9388. 

Ümit Ulusoy, Mehmet Serdar Güzel and Erkan Bostanci (April 22nd 2020). A Q-Learning-Based Approach for Simple and Multi-Agent Systems, Multi Agent Systems - Strategies and Applications, Ricardo López - Ruiz, IntechOpen, DOI: 10.5772/intechopen.88484.

Dennis Barrios-Aranibar and Luiz M. G. Gon&#231;alves (January 1st 2009). Influence Value Q-Learning: A Reinforcement Learning Algorithm for Multi Agent Systems, Theory and Novel Applications of Machine Learning, Meng Joo Er and Yi Zhou, IntechOpen, DOI: 10.5772/6675. 

Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchical multi-agent reinforcement learning (MARL) algorithm with unsupervised skill discovery. Agents learn useful and distinct skills at the low level via independent Q-learning, while they learn to select complementary latent skill variables at the high level via centralized multi-agent training with an extrinsic team reward. The set of low-level skills emerges from an intrinsic reward that solely promotes the decodability of latent skill variables from the trajectory of a low-level skill, without the need for hand-crafted rewards for each skill. For scalable decentralized execution, each agent independently chooses latent skill variables and primitive actions based on local observations. Our overall method enables the use of general cooperative MARL algorithms for training high level policies and single-agent RL for training low level skills. Experiments on a stochastic high dimensional team game show the emergence of useful skills and cooperative team play. The interpretability of the learned skills show the promise of the proposed method for achieving human-AI cooperation in team sports games.

AAMAS 2020

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery

hierarchical learning

option discovery

multi-agent learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

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). 

Networked public goods games model scenarios in which self-interested agents decide whether or how much to invest in an action that benefits not only themselves, but also their network neighbors.
Examples include vaccination, security investment, and crime reporting. While every agent's utility is increasing in their neighbors' joint investment, the specific form can vary widely depending on the scenario. A principal, such as a policymaker, may wish to induce large investment from the agents. Besides direct incentives, an important lever here is the network structure itself: by adding and removing edges, for example, through community meetings, 
the principal can change the nature of the utility functions, resulting in different, and perhaps socially preferable, equilibrium outcomes.
We initiate an algorithmic study of targeted network modifications with the goal of inducing equilibria of a particular form. We study this question for a variety of equilibrium forms (induce all agents to invest, at least a given set S, exactly a given set S, at least k agents), and for a variety of utility functions.
While we show that the problem is NP-complete for a number of these scenarios, we exhibit a broad array of scenarios in which the problem can be solved in polynomial time by non-trivial reductions to (minimum-cost) matching problems.



Inducing Equilibria in Networked Public Goods Games through Network Structure Modification

Reinforcement learning (RL) is a promising technique for optimizing traffic signal controllers that dynamically respond to real-time traffic conditions. Recent efforts that applied Multi-Agent RL (MARL) to this problem have shown remarkable improvement over centralized RL, with the scalability to solve large problems by distributing the global control to local RL agents. Unfortunately, it is also easy to get stuck in local optima because each agent only has partial observability of the environment with limited communication. To tackle this, we borrow ideas from feudal RL and propose a novel MARL approach combining with the feudal hierarchy. Specifically, we split the traffic network into several regions, where each region is controlled by a manager agent and the agents who control the traffic signals are its workers. In our method, managers coordinate their high-level behaviors and set goals for their workers in the region, while each lower-level worker controls traffic signals to fulfill the managerial goals. By doing so, we are able to coordinate globally while retain scalability. We empirically evaluate our method both in a synthetic traffic grid and real-world traffic network using the SUMO simulator. Our experimental results demonstrate that our approach outperforms the state-of-the-art in almost all evaluation metrics commonly used for traffic signal control.

Feudal Multi-Agent Deep Reinforcement Learning for Traffic Signal Control

Motivational interviewing is a counseling technique that involves the in-depth exploration of a person’s reasons for and against changing their behavior, and is particularly effective for substance use counseling. We are developing a computational framework that uses techniques from motivational interviewing to conduct substance use counseling sessions by simulating face-to-face interactions with a virtual agent. We evaluated the feasibility of using a virtual agent system that uses a constrained-input modality and dialogue trees to automate parts of motivational interviewing, and report the results conducted with patients at two substance use treatment facilities. We are extending this prototype to encompass all of motivational interviewing by processing information from unconstrained user speech. To that end, we report results from training a dialog act prediction model on 132 transcripts of patient-provider counseling sessions. Our best model realized an F1 score of 0.62, recall of 0.61, precision of 0.65, and accuracy of 0.6 across five classes. This indicates reasonably good performance, highlighting the potential of this approach.


Towards a Computational Framework for Automating Substance Use Counseling with Virtual Agents

A two-player finite game is represented by two payoff matrices $(A,B)$, one for each player. Imitation games are a subclass of two-player games in which $B$ is the identity matrix, implying that the second player gets a positive payoff only if she ``imitates"" the first. Given that the problem of computing a Nash equilibrium (NE) is known to be provably hard, even to approximate, we ask if it is any easier for imitation games.

We show that much like the general case, for any $c>0$, computing a $\frac{1}{n^c}$-approximate NE of imitation games remains PPAD-hard, where $n$ is the number of moves available to the players. On the other hand, we design a polynomial-time algorithm to find $\epsilon$-approximate NE for any given constant $\epsilon>0$ (PTAS). The former result also rules out the smooth complexity being in $\Ptime$, unless $\PPAD \subset \RP$. 


Approximate Nash Equilibria of Imitation Games: Algorithms and Complexity

In games with Imperfect information players have partial knowledge about their position in the game, which makes it difficult to compute optimal strategies. Here we present several results on computational complexity of games with imperfect information. We also present a generalized model for Bridge Bidding phase to motivate further theoretical study of this phase of Bridge. 


A Bridge between Polynomial Optimization and Games with Imperfect Recall

Cryptocurrenties

Deregulated power systems with high renewable penetration often involve complex decision-making by self-interested private investors. In this work, we study the setting of privately developed and shared network capacity, where the power grid infrastructure, renewable generation and storage units are built by profit-driven investors. Specifically, we consider a case where demand and generation sites are not co-located, and a private investor installs generation capacity and a power line between the two locations providing also access to rival competitors (local generators and storage investors) against a fee. We show such a setting leads to a bilevel Stackelberg-Cournot game between the line investor (leader) and local investors (followers) and develop a data-driven solution to derive the profit-maximising capacities installed by players at equilibrium, based on analysis of a large-scale empirical dataset from a grid upgrade project in the UK. Our method provides a realistic tool to analyse decision-making of private investors in such games and subsequently encourage further adoption of renewable generation.

Strategic Decision-Making for Power Network Investments With Distributed Renewable Generation

Social interactions are key in multi-agent systems. Social dilemmas have been widely studied to model specific problems in social interactions. However, state-of-the-art social dilemmas have disregarded specific ethical aspects affecting interactions.

Here we propose a novel model for social dilemmas, the so-called Sequential Moral Dilemmas, that do capture the notion of moral value. First, we provide a formal definition of sequential moral dilemmas as Markov Games. Thereafter, we formally characterise theoretically the conditions for agents to learn to behave ethically, so that they are aligned with the moral value. Moreover, we exploit our characterisation to provide a structural solution to a sequential moral dilemma, namely how to configure the Markov game to solve the dilemma. 

Finally, we illustrate our proposal through the so-called public civility game, an example of a sequential moral dilemma considering the civility value. We show the social benefits obtained when the agents learn to adhere to the moral value.

A Structural Solution to Sequential Moral Dilemmas

BDI logics, i.e., logics with belief, desire and intention attitudes, are one of the most widely studied formal languages for modelling rational agents. 
In this paper, we consider the logic CTL∗_BDI that augments the branching-time logic CTL∗ with the BDI modalities and adopt the possible-world semantics by Rao and Georgeff. We recall that in this semantics bdi relations vary over time according to a branching-time structure. We study the related model-checking question for finite-state structures, and in particular, we focus on models that are described as tuples of Kripke structures (one for
each world) and where the BDI relations are captured by finite-state relations. Note that for formulas that do not contain BDI modalities this corresponds to standard CTL∗ model-checking that is known to be PSPACE-complete. We show that by adding the BDI modalities
the computational complexity of model-checking remains PSPACE-complete. 
The problem is still PSPACE-hard even if we disallow the nesting of temporal operators in the path formulas, i.e., we restrict to the temporal modalities of CTL. 
Finally, we give a fixed-point formulation of our algorithm for Ctlbdi that implements it on the top of existing symbolic fixed-point solvers.

On the Model-Checking of Branching-time Temporal Logic with BDI Modalities

Bidding and acceptance strategies have a substantial impact on the outcome of negotiations in scenarios with linear additive and nonlinear utility functions. Over the years, it has become clear that there is no single best strategy for all negotiation settings, yet many fixed strategies are still being developed. We envision a shift in the strategy design question from: What is a good strategy?, towards: What could be a good strategy? For this purpose, we developed a method leveraging automated algorithm configuration to find the best strategies for a specific set of negotiation settings. By empowering automated negotiating agents using automated algorithm configuration, we obtain a flexible negotiation agent that can be configured automatically for a rich space of opponents and negotiation scenarios.
To critically assess our approach, the agent was tested in an ANAC-like bilateral automated negotiation tournament setting against past competitors. We show that our automatically configured agent outperforms all other agents, with a 5.1% increase in negotiation payoff compared to the next-best agent. We note that without our agent in the tournament, the top-ranked agent wins by a margin of only 0.01%.

Downloads

Next from AAMAS 2020

Inducing Equilibria in Networked Public Goods Games through Network Structure Modification

Similar lecture

Relative Variational Intrinsic Control

.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

Inducing Equilibria in Networked Public Goods Games through Network Structure Modification

Similar lecture

Relative Variational Intrinsic Control

Downloads