Intention-Aware Multiagent Scheduling

The Belief Desire Intention (BDI) model of agency is a popular and mature paradigm for designing and implementing multiagent systems. There are several agent implementation platforms that follow the BDI model. In BDI systems, the agents typically have to pursue multiple goals, and often concurrently. The way in which the agents commit to achieving their goals forms their intentions. There has been much work on scheduling the intentions of agents. However, most of this work has focused on scheduling the intentions of a single agent with no awareness and consideration of other agents that may be operating in the same environment. They schedule the intentions of the single-agent in order to maximise the total number of goals achieved. In this work, we investigate techniques for scheduling the intentions of an agent in a multiagent setting, where an agent is aware (or partially aware) of the intentions of other agents in the environment. We use a Monte Carlo Tree Search (MCTS) based approach and show that our intention-aware scheduler generates better outcomes in cooperative, neutral (selfish) and adversarial settings than the state-of-the-art schedulers that do not consider other agents’ intentions.

[1]  Sarvapali D. Ramchurn,et al.  Planning Search and Rescue Missions for UAV Teams , 2016, ECAI.

[2]  John Thangarajah,et al.  Progressing Intention Progression: A Call for a Goal-Plan Tree Contest , 2017, AAMAS.

[3]  Winfried Lamersdorf,et al.  Jadex: A BDI Reasoning Engine , 2005, Multi-Agent Programming.

[4]  Shimon Whiteson,et al.  MAVEN: Multi-Agent Variational Exploration , 2019, NeurIPS.

[5]  John Thangarajah,et al.  Robust Execution of BDI Agent Programs by Exploiting Synergies Between Intentions , 2016, AAAI.

[6]  Lin Padgham,et al.  Evaluating coverage based intention selection , 2014, AAMAS.

[7]  Lin Padgham,et al.  Improving domain-independent intention selection in BDI systems , 2015, Autonomous Agents and Multi-Agent Systems.

[8]  Lin Padgham,et al.  Computationally Effective Reasoning About Goal Interactions , 2011, Journal of Automated Reasoning.

[9]  Brian Logan,et al.  Action-Level Intention Selection for BDI Agents , 2016, AAMAS.

[10]  Jos W. H. M. Uiterwijk,et al.  Single-player Monte-Carlo tree search for SameGame , 2012, Knowl. Based Syst..

[11]  Edmund H. Durfee,et al.  Performance of coordinating concurrent hierarchical planning agents using summary information , 2000, Proceedings Fourth International Conference on MultiAgent Systems.

[12]  Eithan Ephrati,et al.  A Framework for the Interleaving of Execution and Planning for Dynamic Tasks by Multiple Agents , 1993, MAAMAW.

[13]  Rafael H. Bordini,et al.  Towards Alternative Approaches to Reasoning About Goals , 2007, DALT.

[14]  Anand S. Rao,et al.  Modeling Rational Agents within a BDI-Architecture , 1997, KR.

[15]  John D. Lowrance,et al.  Planning and reacting in uncertain and dynamic environments , 1995, J. Exp. Theor. Artif. Intell..

[16]  John Thangarajah,et al.  Intention Selection with Deadlines , 2016, ECAI.

[17]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[18]  Michael Wooldridge,et al.  Programming Multi-Agent Systems in AgentSpeak using Jason (Wiley Series in Agent Technology) , 2007 .

[19]  Edmund H. Durfee,et al.  Theory for Coordinating Concurrent Hierarchical Planning Agents Using Summary Information , 1999, AAAI/IAAI.

[20]  Lin Padgham,et al.  Measuring plan coverage and overlap for agent reasoning , 2012, AAMAS.

[21]  Edmund H. Durfee,et al.  Abstract Reasoning for Planning and Coordination , 2002, SARA.

[22]  Demis Hassabis,et al.  Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm , 2017, ArXiv.

[23]  Victor R. Lesser,et al.  AgentSpeak(XL): efficient intention selection in BDI agents via decision-theoretic task scheduling , 2002, AAMAS '02.

[24]  Bart De Schutter,et al.  A Comprehensive Survey of Multiagent Reinforcement Learning , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[25]  Michael Winikoff,et al.  JACKTM Intelligent Agents: An Industrial Strength Platform , 2005, Multi-Agent Programming.

[26]  Brian Logan,et al.  Reasoning About the Executability of Goal-Plan Trees , 2016, EMAS@AAMAS.

[27]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[28]  Pieter Spronck,et al.  Monte-Carlo Tree Search: A New Framework for Game AI , 2008, AIIDE.

[29]  Rafael H. Bordini,et al.  An Alternative Approach for Reasoning about the Goal-Plan Tree Problem , 2010, ECAI.

[30]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[31]  Lin Padgham,et al.  Hierarchical planning in BDI agent programming languages: a formal approach , 2006, AAMAS '06.

[32]  Rob Fergus,et al.  Learning Multiagent Communication with Backpropagation , 2016, NIPS.

[33]  Michael Winikoff,et al.  Detecting & exploiting positive goal interaction in intelligent agents , 2003, AAMAS '03.

[34]  Victor R. Lesser,et al.  Implementing soft real-time agent control , 2001, AGENTS '01.

[35]  Victor Lesser,et al.  Quantitative Modeling of Complex Environments , 1993 .

[36]  Shimon Whiteson,et al.  Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning , 2017, ICML.

[37]  John Thangarajah,et al.  SP-MCTS-based Intention Scheduling for BDI Agents , 2014, ECAI.

[38]  Yi Wu,et al.  Influence-Based Multi-Agent Exploration , 2020, ICLR.