Publications:
2024
- A First Introduction to Cooperative Multi-Agent Reinforcement Learning. Christopher Amato. In arXiv, December 2024. [pdf]
- SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents. Ethan Rathbun, Christopher Amato and Alina Oprea. In the
Proceedings
of the Conference on Neural Information
Processing Systems (NeurIPS-24),
December 2024. [OpenReview]
- Leveraging Mutual Information for Asymmetric Learning under Partial Observability. Hai Nguyen, Long Dinh Van The, Christopher Amato and Robert Platt. In the
Proceedings of the 2023 Conference on Robot Learning
(CoRL-24), November 2024. [OpenReview]
- An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning. Christopher Amato. In arXiv, September 2024. [arXiv]
- Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments. Daniel Melcer, Christopher Amato and Stavros Tripakis. In the
Proceedings of the First Reinforcement Learning Conference (RLC-24), August 2024. [link]
- An Introduction to Decentralized Training and Execution in Cooperative Multi-Agent Reinforcement Learning. Christopher Amato. In arXiv, May 2024. [arXiv]
- Robot Navigation in Unseen Environments using Coarse Maps. Chengguang Xu, Christopher Amato, and Lawson L.S. Wong. In the
Proceedings of the International Conference on Robotics and Automation (ICRA-24), May 2024. [pdf]
2023
- Equivariant Reinforcement Learning under Partial Observability. Hai Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt and Christopher Amato. In the
Proceedings of the 2023 Conference on Robot Learning
(CoRL-23), November 2023. [pdf][website]
- On-Robot Bayesian Reinforcement Learning for POMDPs. Hai Nguyen, Sammie Katt, Yuchen Xiao and Christopher Amato. In the
Proceedings of the IEEE/RSJ
International Conference on Intelligent Robots and Systems
(IROS-23), October 2023. [arXiv]
- On Centralized Critics in Multi-Agent Reinforcement Learning. Xueguang Lyu, Andrea Baisero, Yuchen Xiao, Brett Daley and Christopher Amato. In the
Journal of Artificial Intelligence Research (JAIR), vol. 77: pages 235-294, May, 2023. [link]
- Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. Brett Daley, Martha White, Christopher Amato and Marlos C. Machado. In the
Proceedings of the Fortieth International Conference on Machine Learning (ICML-23),
July 2023. [pdf]
- Safe Deep Reinforcement Learning by Verifying Task-Level Properties. Enrico Marchesini, Luca Marzari, Alessandro Farinelli and Christopher Amato. In the
Proceedings of the Twenty-Second International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-23),
May 2023. [pdf]
- Improving Deep Policy Gradients with Value Function Search. Enrico Marchesini and Christopher Amato. In the
Proceedings of the Eleventh International Conference on Learning Representations (ICLR-23),
May 2023. [OpenReview]
2022
- Deep Transformer Q-Networks for Partially Observable Reinforcement Learning. Kevin Esslinge, Robert Platt and Christopher Amato. In
arXiv, November 2022. [arXiv]
- Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning. Yuchen Xiao, Weihao Tan and Christopher Amato. In the
Proceedings
of the Conference on Neural Information
Processing Systems (NeurIPS-22),
December 2022. [paper, poster and video][pdf]
- Shield Decentralization for Safe Multi-Agent Reinforcement Learning. Daniel Melcer, Stavros Tripakis and Christopher Amato. In the
Proceedings
of the Conference on Neural Information
Processing Systems (NeurIPS-22),
December 2022. [paper, poster and video][pdf]
- Leveraging Fully Observable Policies for Learning under Partial Observability. Hai Nguyen, Andrea Baisero, Dian Wang, Christopher Amato and Robert Platt. In the Proceedings of the
Conference on Robot Learning(CoRL-22),
December 2022. [OpenReview]
- Asymmetric DQN for Partially Observable Reinforcement Learning. Andrea Baisero, Brett Daley and Christopher Amato. In the
Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI-22),
August 2022. [OpenReview]
- Hierarchical Reinforcement Learning under Mixed Observability. Hai Nguyen, Zhihan Yang, Andrea Baisero, Xiao Ma, Robert Platt and Christopher Amato. In the Proceedings of the Fifteenth International Workshop on the Algorithmic Foundations of Robotics (WAFR-22),
June 2022. [pdf][supplement (zip)]
- Unbiased Asymmetric Reinforcement Learning under Partial Observability. Andrea Baisero and Christopher Amato. In the
Proceedings of the International Conference on
Autonomous Agents and Multi-Agent Systems (AAMAS-22),
May 2022. [paper][video]
- BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs. Sammie Katt, Hai Nguyen, Frans Oliehoek and Christopher Amato. In the
Proceedings of the International Conference on
Autonomous Agents and Multi-Agent Systems (AAMAS-22),
May 2022. [paper][video]
- A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning. Xueguang Lyu, Yuchen Xiao, Andrea Baisero and Christopher Amato. In the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-22), February 2022. [paper, poster and video]
2021
- Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning. Yuchen Xiao, Xueguang Lyu and Christopher Amato. In the Proceedings of the International Symposium on Multi-Robot and Multi-Agent Systems (MRS-21), November 2021. [paper] Nominated
for best paper!
- Reconciling Rewards with Predictive State Representations. Andrea Baisero and Christopher Amato. In the
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-21), August 2021. [paper]
- End-to-End Grasping Policies for Human-in-the-Loop Robots via Deep Reinforcement Learning. Mohammadreza Sharif,
Deniz Erdogmus, Christopher Amato and Taskin Padir. In the
Proceedings of the International Conference on Robotics and Automation (ICRA-21), May 2021. [paper]
- Contrasting Centralized and Decentralized Critics in
Multi-Agent Reinforcement Learning. Xueguang Lyu,
Yuchen Xiao, Brett Daley and Christopher Amato. In the
Proceedings of the International Conference on
Autonomous Agents and Multi-Agent Systems (AAMAS-21),
May 2021. [paper] [video] Nominated
for best paper!
- Safe Multi-Agent Reinforcement Learning via Shielding.
Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rudiger
Ehlers, Ufuk Topcu and Lu Feng. In the Proceedings of
the International Conference on Autonomous
Agents and Multi-Agent Systems (AAMAS-21), May 2021. [paper]
[video]
- Multi-Agent Reinforcement Learning with Directed
Exploration and Selective Memory Reuse. Shuo Jiang and
Christopher Amato. In the Proceedings of the
Intelligent Robotics and Multi-Agent Systems Track at the
ACM Symposium on Applied Computing (IRMAS SAC-21),
March 2021. [paper]
2020
- Belief-Grounded Networks for Accelerated Robot Learning
under Partial Observability. Hai Nguyen*, Brett
Daley*, Xinchao Song, Christopher Amato^ and Robert Platt^.
In the Proceedings of the Conference on Robot Learning
(CoRL-20), November 2020. [paper,
code and video]
- Hierarchical Robot Navigation in Novel Environments
using Rough 2-D Maps. Chengguang Xu, Christopher
Amato and Lawson Wong. In the Proceedings of the
Conference on Robot Learning (CoRL-20), November 2020.
[paper, code
and video]
- Hybrid Independent Learning in Cooperative Markov
Games. Roi Yehoshua and Christopher Amato. In the
Proceedings of the International Conference on Distributed
Artificial Intelligence (DAI-20), October 2020. [paper
forthcoming]
- To Ask or Not to Ask: A User Annoyance Aware Preference
Elicitation Framework for Social Robots. Balint
Gucsi, Danesh Tarapore, William Yeoh, Christopher Amato and
Long Tran-Thanh. In the Proceedings of the IEEE/RSJ
International Conference on Intelligent Robots and Systems
(IROS-20), October 2020. [paper]
- Towards End-to-End Control of a Robot Prosthetic Hand
via Reinforcement Learning. Mohammadreza Sharif,
Deniz Erdogmus, Christopher Amato and Taskin Padir. In the
Proceedings of the 8th IEEE RAS/EMBS International
Conference on Biomedical Robotics and Biomechatronics
(BioRob-20), December 2020. [paper forthcoming]
- Learning Multi-Robot Decentralized Macro-Action-Based
Policies via a Centralized Q-net. Yuchen Xiao,
Joshua Hoffman, Tian Xia and Christopher Amato. In the
Proceedings of the International Conference on Robotics
and Automation (ICRA-20), May 2020. [paper]
[video]
- Likelihood Quantile Networks for Coordinating
Multi-Agent Reinforcement Learning. Xueguang Lyu and
Christopher Amato. In the Proceedings of the
International Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-20), May 2020. [paper]
2019
- Reconciling λ-Returns with Experience Replay.
Brett Daley and Christopher Amato. In the Proceedings
of the Conference on Neural Information
Processing Systems (NeurIPS-19), December 2019. [paper]
- Macro-Action-Based Deep Multi-Agent Reinforcement
Learning. Yuchen Xiao, Joshua Hoffman and
Christopher Amato. In the Proceedings of the Conference
on Robot Learning (CoRL-19), October 2019. [paper]
- Online Planning for Target Object Search in Clutter
under Partial Observability. Yuchen Xiao, Sammie
Katt, Andreas ten Pas, Shengjian Chen and Christopher Amato.
In the Proceedings of the 2019 IEEE International
Conference on Robotics and Automation (ICRA-19), May
2019. [paper] [video]
- Bayesian Reinforcement Learning in Factored POMDPs.
Sammie Katt, Frans A. Oliehoek and Christopher Amato. In the
Proceedings of the Eighteenth International Conference
on Autonomous Agents and Multi-Agent Systems
(AAMAS-19), May 2019. [paper]
- Modeling and Planning with Macro-Actions in
Decentralized POMDPs. Christopher Amato, George
Konidaris, Jonathan P. How and Leslie P. Kaelbling. In the
Journal of Artificial Intelligence Research (JAIR),
vol. 64: pages 817-859, March, 2019. [paper]
[link]
- Learning to Teach in Cooperative
Multiagent Reinforcement Learning. Shayegan
Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro, Matthew
Riemer, Christopher Amato, Murray Campbell and Jonathan How.
In the Proceedings of the Thirty-Third AAAI Conference
on Artificial Intelligence (AAAI-19), February 2019. [arXiv
link] Outstanding
student paper honorable mention!
2018
- The Art of Drafting: A Team-Oriented Hero
Recommendation System for Multiplayer Online Battle Arena
Games. Zhengxing Chen, Truong-Huy D. Nguyen, Yuyu
Xu, Christopher Amato, Seth Cooper, Yizhou Sun and Magy Seif
El-Nasr. In the Proceedings of the ACM Conference on
Recommender Systems (Recsys-18), October 2018. [paper
forthcoming]
- Q-DeckRec: a Fast Deck Recommendation System for
Collectible Card Games. Zhengxing Chen, Christopher
Amato, Truong-Huy D. Nguyen, Seth Cooper, Yizhou Sun and
Magy Seif El-Nasr. In the Proceedings of the IEEE
Conference on Computational Intelligence and Games
(CIG-18), August 2018. [paper forthcoming]
- Decision-Making Under Uncertainty in Multi-Agent and
Multi-Robot Systems: Planning and Learning.
Christopher Amato. In the Proceedings of the
Twenty-Seventh International Joint Conference on
Artificial Intelligence (IJCAI-18), July 2018. [paper]
- Near-Optimal Adversarial Policy
Switching for Decentralized Asynchronous Multi-Agent
Systems. Nghia Hoang, Yuchen Xiao, Kavinayan
Sivakumar, Christopher Amato and Jonathan P. How. In the
Proceedings of the 2018 IEEE International Conference on
Robotics and Automation (ICRA-18), May 2018.
[paper] [video]
2017
- Learning for Multi-robot Cooperation in Partially
Observable Stochastic Environments with Macro-actions.
Miao Liu, Kavinayan Sivakumar, Shayegan Omidshafiei,
Christopher Amato and Jonathan P. How. In the
Proceedings of the 2017 IEEE/RSJ International Conference
on Intelligent Robots and Systems (IROS-17),
September 2017. [paper]
[video]
- Deep Decentralized Multi-Task Multi-Agent Reinforcement
Learning under Partial Observability. Shayegan
Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How
and John Vian. In the Proceedings of the Thirty-Fourth
International Conference on Machine Learning
(ICML-17), August 2017. [paper]
[link]
- Learning in POMDPs with Monte Carlo Tree Search.
Sammie Katt, Frans A. Oliehoek and Christopher Amato. In the
Proceedings of the Thirty-Fourth International
Conference on Machine Learning (ICML-17), August
2017. [paper] [link]
- COG-DICE: An Algorithm for Solving
Continuous-Observation Dec-POMDPs. Madison
Clark-Turner and Christopher Amato. In the Proceedings
of the Twenty-Sixth International Joint Conference on
Artificial Intelligence (IJCAI-17), August 2017. [paper]
- Scalable Accelerated Decentralized Multi-Robot Policy
Search in Continuous Observation Spaces. Shayegan
Omidshafiei, Christopher Amato, Miao Liu, Jonathan P. How,
John Vian. In the Proceedings of the 2017 IEEE
International Conference on Robotics and Automation
(ICRA-17), May 2017. [paper]
- Semantic-level Decentralized
Multi-Robot Decision-Making using Probabilistic
Macro-Observations. Shayegan Omidshafiei,
Shih-Yuan Liu, Michael Everett, Brett Lopez, Christopher
Amato, Miao Liu, Jonathan P. How, John Vian. In the
Proceedings of the 2017 IEEE International Conference on
Robotics and Automation (ICRA-17), May 2017. [paper]
[video]
- Decentralized Control of Multi-Robot Partially
Observable Markov Decision Processes using Belief Space
Macro-actions. Shayegan Omidshafiei, Ali-akbar
Agha-mohammadi, Christopher Amato, Shih-Yuan Liu and
Jonathan P. How. In the International Journal of
Robotics Research (IJRR), vol. 36, Issue 2, 2017.
[paper][link]
- Policy Search for Multi-Robot Coordination under
Uncertainty. Christopher Amato, George Konidaris,
Ariel Anders, Gabriel Cruz, Jonathan P. How and Leslie P.
Kaelbling. In the International Journal of Robotics
Research (IJRR), vol. 35, issue 14, 2017. [paper]
[link]
2016
- A Concise Introduction to
Decentralized POMDPs. Frans A. Oliehoek
and Christopher Amato. SpringerBriefs in Intelligent
Systems, Springer, 2016. [Author
pre-print] [link
to book website] [SpringerLink]
- Optimally Solving Dec-POMDPs as Continuous-State MDPs.
Jilles S. Dibangoye, Christopher Amato, Olivier Buffet and
François Charpillet. In the Journal of Artificial
Intelligence Research (JAIR), 2016. [link]
- Graph-based Cross Entropy Method for Solving
Multi-Robot Decentralized POMDPs. Shayegan
Omidshafiei, Ali-akbar Agha-mohammadi, Christopher Amato,
Shih-Yuan Liu, Jonathan P. How and John Vian. In the
Proceedings of the 2016 IEEE International Conference on
Robotics and Automation (ICRA-16), May 2016. [paper]
- Learning for Decentralized Control of Multiagent
Systems in Large Partially Observable Stochastic
Environments. Miao Liu, Christopher Amato, J. Daniel
Griffith, Emily Anesta and Jonathan P. How. In the Proceedings
of the Thirtieth AAAI Conference on Artificial
Intelligence (AAAI-16), February 2016. [paper]
[supplementary
material]
2015
- Cooperative Decision Making.
Christopher Amato. In Decision Making Under
Uncertainty: Theory and Application edited by Mykel J.
Kochenderfer. MIT Press, 2015. [paper]
[book
website]
- Policy Search for Multi-Robot
Coordination under Uncertainty. Christopher
Amato, George Konidaris, Ariel Anders, Gabriel Cruz,
Jonathan P. How and Leslie P. Kaelbling. In Proceedings
of the 2015 Robotics: Science and Systems Conference
(RSS-15), July 2015. [paper]
Nominated
for best paper!
- Stick-Breaking Policy Learning in
Decentralized POMDPs. Miao Liu, Christopher
Amato, Xuejun Liao, Jonathan P. How and Lawrence Carin. In Proceedings
of the Twenty-Fourth International Joint Conference on
Artificial Intelligence (IJCAI-15), July 2015. [paper]
[arXiv link to
extended version]
- Planning for Decentralized Control of
Multiple Robots Under Uncertainty. Christopher
Amato, George Konidaris, Gabriel Cruz, Christopher A.
Maynor, Jonathan P. How and Leslie P. Kaelbling. In Proceedings
of the 2015 IEEE International Conference on Robotics and
Automation (ICRA-15), May 2015. [paper]
- Decentralized Control of Partially
Observable Markov Decision Processes using Belief Space
Macro-Actions. Shayegan Omidshafiei, Ali-akbar
Agha-mohammadi, Christopher Amato and Jonathan P. How. In Proceedings
of the 2015 IEEE International Conference on Robotics and
Automation (ICRA-15), May 2015. [paper]
- Scalable Planning and Learning for
Multiagent POMDPs. Christopher Amato and
Frans A. Oliehoek. In Proceedings of the Twenty-Ninth
AAAI Conference on Artificial Intelligence (AAAI-15),
January 2015. [paper]
[extended
version]
2014
- Dec-POMDPs as Non-Observable MDPs. Frans A.
Oliehoek and Christopher Amato. Technical Report
IAS-UVA-14-01, Intelligent Systems Lab, University of
Amsterdam, 2014. October 2014. [paper]
- Decentralized Decision-Making Under Uncertainty for
Multi-Robot Teams. Christopher Amato, George
Konidaris, Jonathan P. How and Leslie P. Kaelbling. In Proceedings
of the Future of Multiple Robot Research and its Multiple
Identities at the International Conference on
Intelligent Robots and Systems (IROS-14), September 2014. [paper]
- Combined Planning Under Uncertainty for Communication
and Control in Multi-Robot Teams. Christopher Amato,
George Konidaris, Jonathan P. How and Leslie P. Kaelbling.
In Proceedings of the Workshop on Communication-aware
Robotics: New Tools for Multi-Robot Networks, Autonomous
Vehicles, and Localization (CarNet) at Robotics:
Science and Systems Conference (RSS-14), July 2014. [paper
forthcoming]
- Graph-Based Planning to Solve Multi-Agent POMDPs.
Ali-akbar Agha-mohammadi, Shayegan Omidshafiei, Christopher
Amato and Jonathan P. How. In Proceedings of the
Workshop on Distributed Control and Estimation for Robotic
Vehicle Networks at Robotics: Science and Systems
Conference (RSS-14), July 2014. [paper forthcoming]
- Planning for Decentralized Control
of Multiple Robots Under Uncertainty. Christopher
Amato, George Konidaris, Gabriel Cruz, Christopher A.
Maynor, Jonathan P. How and Leslie P. Kaelbling. In Proceedings
of the Workshop on Planning and Robotics (PlanRob) at
the Twenty-Fourth International Conference on Automated
Planning and Scheduling (ICAPS-14), Portsmouth, NH, June
2014. [paper]
[arXiv link of
previous version]
- Planning with Macro-Actions in
Decentralized POMDPs. Christopher Amato, George
Konidaris and Leslie P. Kaelbling. In Proceedings of the
Thirteenth International Conference on Autonomous Agents
and Multi-Agent Systems (AAMAS-14), May 2014. [paper]
- Exploiting
Separability in Multi-Agent Planning with
Continuous-State MDPs. Jilles S. Dibangoye,
Christopher Amato, Olivier Buffet and François Charpillet.
In Proceedings of the Thirteenth International
Conference on Autonomous Agents and Multi-Agent Systems
(AAMAS-14), May 2014. [paper]
Won best
paper!
2013
- Decentralized Control of Partially
Observable Markov Decision Processes. Christopher
Amato, Girish Chowdhary, Alborz Geramifard, Nazim Kemal Ure
and Mykel J. Kochenderfer. In Proceedings of the
Fifty-Second IEEE Conference on Decision and Control
(CDC-13), Florence, Italy, December 2013. [paper]
- Scalable Bayesian Reinforcement
Learning for Multiagent POMDPs.
Christopher Amato, Frans A. Oliehoek and Eric Shyu. In Proceedings
of the Multidisciplinary Conference on Reinforcement
Learning and Decision Making (RLDM-13), Princeton,
NJ, October 2013. [paper forthcoming]
- Optimally
Solving Dec-POMDPs as Continuous-State MDPs.
Jilles S. Dibangoye, Christopher Amato, Olivier Buffet and
François Charpillet. In Proceedings of the Twenty-Third
International Joint Conference on Artificial Intelligence
(IJCAI-13), Beijing, China, August 2013. [paper]
- Incremental Clustering and Expansion
for Faster Optimal Planning in Decentralized POMDPs.
Frans A. Oliehoek, Matthijs T. J. Spaan, Christopher
Amato and Shimon Whiteson. Journal of Artificial
Intelligence Research (JAIR), 2013. [link]
- Bayesian Reinforcement Learning for
Multiagent Systems with State Uncertainty.
Christopher Amato and Frans A. Oliehoek. In Proceedings
of the Workshop on Multi-Agent Sequential Decision Making
in Uncertain Domains (MSDM) at the Twelfth
International Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-13), Saint Paul, MN, May 2013.
[paper forthcoming]
- Producing Efficient Error-bounded
Solutions for Transition Independent Decentralized MDPs.
Jilles S. Dibangoye, Christopher Amato, Arnaud Doniec
and François Charpillet. In Proceedings of the Twelfth
International Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-13), Saint Paul, MN, May
2013. [paper]
2012
- Diagnose and Decide: An Optimal
Bayesian Approach. Christopher Amato and Emma
Brunskill. In Proceedings of the Workshop on Bayesian
Optimization & Decision Making at the
Twenty-Sixth Annual Conference on Neural Information
Processing Systems (NIPS-12), Lake Tahoe, NV, December 2012.
[paper]
- Scaling Up Decentralized MDPs Through
Heuristic Search. Jilles S. Dibangoye,
Christopher Amato and Arnaud Doniec. In Proceedings of
the Twenty-Eighth Conference on Uncertainty in Artificial
Intelligence (UAI-12), Catalina Island, California,
August 2012. [paper]
- Using POMDPs to Control an
Accuracy-Processing Time Tradeoff in Video Surveillance.
Komal Kapoor, Christopher Amato, Nisheeth Srivastava and
Paul Schrater. In Proceedings of the Twenty-Fourth
Annual Conference on Innovative Applications of Artificial
Intelligence (IAAI-12), Toronto, Canada, July 2012. [paper]
2011
- Decision Support in Organizations: A
Case for OrgPOMDPs. Pradeep Varakantham, Nathan
Schur, Alan Carlin and Christopher Amato. In
Proceedings of the 2011 IEEE/WIC/ACM International
Conference on Intelligent Agent Technology (IAT-11),
Lyon, France, August 2011. [paper forthcoming]
- Scaling Up Optimal Heuristic Search
in Dec-POMDPs via Incremental Expansion. Frans
A. Oliehoek, Matthijs T. J. Spaan and Christopher Amato. In
Proceedings of the Twenty-Second International Joint
Conference on Artificial Intelligence (IJCAI-11),
Barcelona, Spain, July, 2011. [paper]
- Adaptive Decision Support for
Structured Organizations: A Case for OrgPOMDPs.
Pradeep Varakantham, Nathan Schur, Alan Carlin and
Christopher Amato. Short Paper to in Proceedings of the
Tenth International Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-11), Taipei, Taiwan, May
2011. [paper forthcoming]
- Towards Realistic Decentralized
Modeling for Use in a Real-World Personal Assistant
Agent Scenario. Christopher Amato, Nathan
Schurr and Paul Picciano. In Proceedings of the
Workshop on Optimisation in Multi-Agent Systems
(OptMAS) at the Tenth International Conference on Autonomous
Agents and Multi-Agent Systems (AAMAS-11), Taipei, Taiwan,
May 2011. [paper]
- Decentralized Models for Use in a
Real-World Personal Assistant Agent Scenario.
Christopher Amato, Nathan Schurr and Paul Picciano. Proceedings
of the AAAI Spring Symposium entitled Help Me Help You:
Bridging the Gaps in Human-Agent Collaboration,
Stanford, California, March, 2011. [paper forthcoming]
2010
- Increasing Scalability in Algorithms
for Centralized and Decentralized Partially Observable
Markov Decision Processes: Efficient Decision-Making and
Coordination in Uncertain Environments.
Christopher Amato. Ph.D. Dissertation, May, 2010. [paper]
- Finite-state controllers based on
Mealy machines for centralized and decentralized POMDPs.
Christopher Amato, Blai Bonet and Shlomo Zilberstein.
Proceedings of the Twenty-Fourth National Conference on
Artificial Intelligence (AAAI-10), Atlanta, GA, July,
2010. [paper]
- High-level Reinforcement Learning
in Strategy Games.
Christopher Amato and Guy Shani. Proceedings of the
Ninth International Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-10), Toronto, Canada,
May, 2010. [paper]
- Solving Identical Payoff Bayesian
Games with Heuristic Search. Frans A. Oliehoek,
Matthijs T. J. Spaan, Jilles S. Dibangoye and Christopher
Amato. Proceedings of the Ninth International Conference
on Autonomous Agents and Multi-Agent Systems
(AAMAS-10), Toronto, Canada, May, 2010. [paper]
2009
- Optimizing Fixed-size Stochastic
Controllers for POMDPs and Decentralized POMDPs.
Christopher Amato, Daniel S. Bernstein and Shlomo
Zilberstein. Journal of Autonomous Agents and Multi-Agent
Systems (JAAMAS) 2009. [paper]
- Incremental Policy Generation for
Finite-Horizon DEC-POMDPs. Christopher Amato,
Jilles Steeve Dibangoye and Shlomo Zilberstein. Proceedings
of the Nineteenth International Conference on Automated
Planning and Scheduling (ICAPS-09), Thessaloniki,
Greece, September, 2009. [paper]
- Achieving Goals in Decentralized
POMDPs. Christopher Amato and Shlomo
Zilberstein. Proceedings of the Eighth International
Joint Conference on Autonomous Agents and Multi-Agent
Systems (AAMAS-09), Budapest, Hungary, May, 2009. [paper]
- Policy Iteration for Decentralized
Control of Markov Decision Processes. Daniel S.
Bernstein, Christopher Amato, Eric A. Hansen and Shlomo
Zilberstein. Journal of AI Research (JAIR), vol. 34,
pages 89-132, February, 2009. [paper]
2008
- Policy Iteration for Decentralized
Control of Markov Decision Processes. Daniel S.
Bernstein, Christopher Amato, Eric A. Hansen and Shlomo
Zilberstein. University of Massachusetts, Department of
Computer Science Tech Report UM-CS-2008-044 , December,
2008. [paper]
- What's Worth Memorizing:
Attribute-based Planning for DEC-POMDPs.
Christopher Amato and Shlomo Zilberstein. Proceedings of
the Multiagent Planning Workshop (MASPLAN) at the
Eighteenth International Conference on Automated Planning
and Scheduling (ICAPS-08), Sydney, Australia, September,
2008. [paper]
- Optimizing Fixed-Size Stochastic
Controllers for POMDPs. Christopher Amato,
Daniel S. Bernstein and Shlomo Zilberstein. Proceedings
of the Workshop on Advancements in POMDP Solvers at
the Twenty-Third International Conference on Artificial
Intelligence (AAAI-08), Chicago, Illinois, July, 2008. [paper]
- Heuristic Policy Iteration for
Infinite-Horizon Decentralized POMDPs.
Christopher Amato, and Shlomo Zilberstein. Proceedings
of the Workshop on Multi-Agent Sequential Decision Making
in Uncertain Domains (MSDM) at the Seventh
International Joint Conference on Autonomous Agents and
Multi-Agent Systems (AAMAS-08), Estoril, Portugal, May,
2008. [paper]
2007
- Optimizing Fixed-Size Stochastic
Controllers for POMDPs and Decentralized POMDPs.
Christopher Amato, Daniel S. Bernstein and Shlomo
Zilberstein. University of Massachusetts, Department of
Computer Science Tech Report UM-CS-2007-70, December, 2007.
[paper]
- Optimizing Memory-Bounded Controllers
for Decentralized POMDPs. Christopher Amato,
Daniel S. Bernstein and Shlomo Zilberstein. Proceedings
of the Twenty-Third Conference on Uncertainty in
Artificial Intelligence, (UAI-07) Vancouver, BC,
Canada, July, 2007. [paper(corrected)]
- Bounded Dynamic Programming for
Decentralized POMDPs. Christopher Amato, Alan
Carlin and Shlomo Zilberstein. Proceedings of the
Workshop on Multi-Agent Sequential Decision Making in
Uncertain Domains (MSDM) at the Sixth International
Joint Conference on Autonomous Agents and Multi-Agent
Systems (AAMAS-07) , Honolulu, Hawai'i, May, 2007. [paper]
- Solving POMDPs Using Quadratically
Constrained Linear Programs. Christopher Amato,
Daniel S. Bernstein and Shlomo Zilberstein. Proceedings
of the Twentieth International Joint Conference on
Artificial Intelligence (IJCAI-07), Hyderabad, India,
January, 2007. [paper]
2006
- Optimal Fixed-Size Controllers for
Decentralized POMDPs. Christopher Amato, Daniel
S. Bernstein and Shlomo Zilberstein. Proceedings of the
Workshop on Multi-Agent Sequential Decision Making in
Uncertain Domains (MSDM) at the Fifth International
Joint Conference on Autonomous Agents and Multi-Agent
Systems (AAMAS) , Future University-Hakodate, May, 2006. [paper]
2005
2004
|
