Leo Raju and Antony Amalraj Morais (April 22nd 2020). Multi-Agent Systems Based Advanced Energy Management of Smart Micro-grid, Multi Agent Systems - Strategies and Applications, Ricardo López - Ruiz, IntechOpen, DOI: 10.5772/intechopen.90402.

Khair Eddin Sabri, Ridha Khedri and Jason Jaskolka (October 1st 2009). Algebraic Model for Agent Explicit Knowledge in Multi-agent Systems, Advanced Technologies, Kankesu Jayanthakumaran, IntechOpen, DOI: 10.5772/8211. 

New Zealand

We study the synthesis of policies for multi-agent systems to implement spatial-temporal tasks. We formalize the problem as a factored Markov decision process subject to so-called graph temporal logic specifications. The transition function and the spatial-temporal task of each agent depend on the agent itself and its neighboring agents. The structure in the model and the specifications enable to develop a distributed algorithm that, given a factored Markov decision process and a graph temporal logic formula, decomposes the synthesis problem into a set of smaller synthesis problems, one for each agent. We prove that the algorithm runs in time linear in the total number of agents. The size of the synthesis problem for each agent is exponential only in the number of neighboring agents,
which is typically much smaller than the number of agents. We demonstrate the algorithm in case studies on disease control and urban security. The numerical examples show that the algorithm can scale to hundreds of agents.
&quot;


AAMAS 2020

Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications

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.

We study the synthesis of policies for multi-agent systems to implement spatial-temporal tasks. We formalize the problem as a factored Markov decision process subject to so-called graph temporal logic specifications. The transition function and the spatial-temporal task of each agent depend on the agent itself and its neighboring agents. The structure in the model and the specifications enable to develop a distributed algorithm that, given a factored Markov decision process and a graph temporal logic formula, decomposes the synthesis problem into a set of smaller synthesis problems, one for each agent. We prove that the algorithm runs in time linear in the total number of agents. The size of the synthesis problem for each agent is exponential only in the number of neighboring agents,
which is typically much smaller than the number of agents. We demonstrate the algorithm in case studies on disease control and urban security. The numerical examples show that the algorithm can scale to hundreds of agents.
"


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). 

This work presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal, expressed as a temporal logic formula, with maximal probability. Enforcing the RL agent to stay safe during learning might limit the exploration, however we show that the proposed architecture is able to automatically handle the trade-off between efficient progress in exploration (towards goal satisfaction) and ensuring safety. Theoretical guarantees are available on the optimality of the synthesised policies and on the convergence of the learning algorithm. Experimental results are provided to showcase the performance of the proposed method.

Cautious Reinforcement Learning with Logical Constraints

Law codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that agents must be accountable and explainable by referring to which rules justify their decisions. The need for explanations is associated with user acceptance and trust. This paper's contribution is twofold: i) we propose an argumentation-based human-agent architecture to map human regulations into a culture for artificial agents with explainable behaviour. Our architecture leans on the notion of argumentative dialogues and generates explanations from the history of such dialogues, and ii) we validate our architecture with a user study in the context of human-agent path deconfliction. Our results show that explanations provide a significantly higher improvement in human performance when systems are more complex. Consequently, we argue that the criteria defining the need of explanations should also consider the complexity of a system. Qualitative findings show that when rules are more complex, explanations significantly reduce the perception of challenge for humans.

Culture-Based Explainable Human-Agent Deconfliction

Ontology alignments enable agents to communicate while preserving heterogeneity in their information. Alignments may not be provided as input and should be able to evolve when communication fails or when new information contradicting the alignment is acquired. In the Alignment Repair Game (ARG) this evolution is achieved via adaptation operators. ARG was evaluated experimentally and the experiments showed that agents converge towards successful communication and improve their alignments. However, whether the adaptation operators are formally correct, complete or redundant is still an open question. In this presentation, we introduce a formal framework based on Dynamic Epistemic Logic that allows us to answer this question. This framework allows us (1) to express the ontologies and alignments used, (2) to model the ARG adaptation operators through announcements and conservative upgrades and (3) to formally establish the correctness, partial redundancy and incompleteness of the adaptation operators in ARG.


Agent Ontology Alignment Repair through Dynamic Epistemic Logic

Swarms can be applied in many relevant domains, such as patrolling or rescue. They usually follow simple local rules, leading to complex emergent behavior. Given their wide applicability, an agent may need to take decisions in an environment containing a swarm that is not under its control, and that may even be an antagonist. Predicting the behavior of each swarm member is a great challenge, and must be done under real time constraints, since they usually move constantly following quick reactive algorithms. We propose the first two solutions for this novel problem, showing integrated on-line learning and planning for decision-making with unknown swarms: (i) we learn an ellipse abstraction of the swarm based on statistical models, and predict its future parameters using time-series; (ii) we learn algorithm parameters followed by each swarm member, in order to directly simulate them. We find in our experiments that we are significantly faster to reach an objective than local repulsive forces, at the cost of success rate in some situations. Additionally, we show that this is a challenging problem for reinforcement learning.


Real-time Learning and Planning in Environments with Swarms: A Hierarchical and a Parameter-based Simulation Approach

This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning from Demonstrations, for example behavior cloning, can lead to proficient policies given limited data. However, it is currently unclear how to efficiently update that policy using reinforcement learning as these approaches are inherently optimizing different objective functions. Previous works have used loss functions, which combine behavior cloning losses with reinforcement learning losses to enable this update. However, the components of these loss functions are often set anecdotally, and their individual contributions are not well understood. In this work, we propose the Cycle-of-Learning (CoL) framework that uses an actor-critic architecture with a loss function that combines behavior cloning and 1-step Q-learning losses with an off-policy pre-training step from human demonstrations. This enables transition from behavior cloning to reinforcement learning without performance degradation and improves reinforcement learning in terms of overall performance and training time. Additionally, we carefully study the composition of these combined losses and their impact on overall policy learning. We show that our approach outperforms state-of-the-art techniques for combining behavior cloning and reinforcement learning for both dense and sparse reward scenarios. Our results also suggest that directly including the behavior cloning loss on demonstration data helps to ensure stable learning and ground future policy updates.


Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments

We present a general model for the operation of a cloud computing server comprised of one or more speed-scalable processors. Typically, tasks are submitted to such a cloud computing server in an online fashion, and the server operator has to schedule the tasks and decides on payments without knowledge about the tasks arriving in the future. Although very natural, this cloud computing problem on speed-scalable processors has not been studied from a mechanism design perspective in the online setting.

We provide a mechanism for this setting, both for a single and multiprocessor environment, that has several desirable properties: (1) the induced game admits a subgame perfect equilibrium in pure strategies and therefore a pure Nash equilibrium, (2) the Price of Anarchy is constant, (3) the mechanism is budget balanced, i.e., the sum of the payments of the agents is equal to the total energy costs, (4) the communication complexity is low, (5) the mechanism is computationally tractable for both the service operator and the agents, and (6) the agents' payment is also intuitive and easy to communicate to them. We also provide a second mechanism with a better Price of Anarchy, which in turn is more involved to implement.

We are able to extend our mechanisms and results to the Bayesian setting, where the type of each agent is drawn independently from some underlying distribution and agents are minimizing their expected costs. In this setting we also show the same approximation factor of our mechanism as in the basic online setting in both the single and the multiprocessor environment.


A General Framework for Energy-Efficient Cloud Computing Mechanisms

Moving nodes in a Mobile Wireless Sensor Network (MWSN) typically have two maintenance objectives: (i) extend the coverage of the network as long as possible to a target area, and (ii) extend the longevity of the network as much as possible. 
As nodes move and also route traffic in the network, their battery levels deplete differently for each node. 
Dead nodes lead to loss of connectivity and even to disengaging full parts of the network. 
Several reactive and rule-based approaches have been proposed to solve this issue by adapting redeployment to depleted nodes. 
However, in large networks a cooperative approach may increase performance by taking the evolution of node battery and traffic into account. 
In this paper, we present a hybrid agent-based architecture that addresses the problem of depleting nodes during the maintenance phase of a MWSN. 
Agents, each assigned to a node, collaborate and adapt their behaviour to their battery levels. 
The collaborative behavior is modeled through the willingness to interact abstraction, which defines when agents ask and give help to one another. 
Thus, depleting nodes may ask to be replaced by healthier counterparts and move to areas with less traffic or to a collection point. 
At the lower level, negotiations trigger a reactive navigation behaviour based on Social Potential Fields (SPF). 
It is shown that the proposed method improves coverage and extends network longevity in an environment without obstacles as compared to SPF alone.

Adaptive Autonomy in Wireless Sensor Networks

Reinforcement learning has been successful in training autonomous agents to accomplish goals in complex environments. Although this has been adapted to multiple settings, including robotics and computer games, human players often find it easier to obtain higher rewards in some environments than reinforcement learning algorithms. This is especially true of high-dimensional state spaces where the reward obtained by the agent is sparse or extremely delayed. In this presentation, we introduce the FRESH (Feedback-based REward SHaping) framework, which eﬀectively integrates feedback signals supplied by a human operator with deep reinforcement learning algorithms in high-dimensional state spaces. During training, a human operator is presented with trajectories from a replay buﬀer and then provides feedback on states and actions in the trajectory. In order to generalize feedback signals provided by the human operator to previously unseen states and actions at test-time, we use a feedback neural network. We use an ensemble of neural networks with a shared network architecture to represent model uncertainty and the confidence of the neural network in its output. The output of the feedback neural network is converted to a shaping reward that is augmented to the reward provided by the environment. We evaluate our approach on the Bowling and Skiing Atari games in the arcade learning environment. Although human experts have achieved high scores in these environments, state-of-the-art deep learning algorithms perform poorly. We observe that FRESH achieves much higher scores than state-of-the-art deep learning algorithms in both environments. FRESH also achieves a 21.4% higher score than a human expert in Bowling and does as well as an expert in Skiing.

FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback

When multiple agents learn in a decentralized manner, the environment appears non-stationary from the perspective of an individual agent due to the exploration and learning of the other agents. Recently proposed deep multi-agent reinforcement learning methods have tried to mitigate this non-stationarity by attempting to determine which samples are from other agent exploration or suboptimality and take them less into account during learning. Based on the same philosophy, this paper introduces a decentralized quantile estimator, which aims to improve performance by distinguishing non-stationary samples based on the likelihood of returns. In particular, each agent considers the likelihood that other agent exploration and policy changes are occurring, essentially utilizing the agent’s own estimations to weigh the learning rate that should be applied towards the given samples. We introduce a formal method of calculating differences of our return distribution representations and methods for utilizing it to guide updates. We also explore the effect of risk-seeking strategies for adjusting learning over time and propose adaptive risk distortion functions which guides risk sensitivity. Our experiments, on traditional benchmarks and new domains, show our methods are more stable, sample efficient and more likely to converge to a joint optimal policy than previous methods.


Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning

Previous approaches to adversary modeling in network security games (NSGs) have been caught in the paradigm of first building a full adversary model, either from expert input or historical attack data, and then solving the game. Motivated by the need to disrupt the multibillion dollar illegal smuggling networks, such as wildlife and drug trafficking, this paper introduces a fundamental shift in learning adversary behavior in NSGs by focusing on the accuracy of the model using the downstream game that will be solved. Further, the paper addresses technical challenges in building such a game-focused learning model by i) applying graph convolutional networks to NSGs to achieve tractability and differentiability and ii) using randomized block updates of the coefficients of the defender's optimization in order to scale the approach to large networks. We show that our game-focused approach yields scalability and higher defender expected utility than models trained for accuracy only.

Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications

Downloads

Next from AAMAS 2020

Cautious Reinforcement Learning with Logical Constraints

Similar lecture

AMOM: Adaptive Masking over Masking for Conditional Masked Language Model

Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications

.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

Cautious Reinforcement Learning with Logical Constraints

Similar lecture

AMOM: Adaptive Masking over Masking for Conditional Masked Language Model

Downloads