AIConfPaper
← Search

Christopher Amato

36 accepted papers

2026

Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations

Enrico Marchesini, Eva Boguslawski, Alessandro Leite, Christopher Amato, Matthieu DUSSARTRE, Marc Schoenauer +2
ICLR 2026poster

Improving power grid operations is essential for enhancing flexibility and accelerating grid decarbonization. Reinforcement learning (RL) has shown promise in this domain, most notably through the Learning to Run a Power Network competitions, but prior work has primarily focused on single-agent sett…

Cited by 0Source ↗Scholar ↗
2026

Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning

Ethan Rathbun, Wo Wei Lin, Alina Oprea, Christopher Amato
ICLR 2026poster

Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to al…

Cited by 0Source ↗Scholar ↗
2026

Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic

Shuo Liu, Tianle Chen, Ryan Amiri, Christopher Amato
ICML 2026poster

Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL). However, most MARL fine-tuning approaches rely on predefined execution protocols, which often require centralized execution. Decentralized LLM collaboration is more appealing in practice, as agen…

Cited by 0Source ↗Scholar ↗
2025

Adversarial Inception Backdoor Attacks against Reinforcement Learning

Ethan Rathbun, Alina Oprea, Christopher Amato
ICML 2025poster

Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adversarial behavior in the agent upon observing a fixed trigger during deployment w…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Leveraging Mutual Information for Asymmetric Learning under Partial Observability

Hai Huu Nguyen, Long Dinh Van The, Christopher Amato, Robert Platt
CoRL 2024poster

Even though partial observability is prevalent in robotics, most reinforcement learning studies avoid it due to the difficulty of learning a policy that can efficiently memorize past events and seek information. Fortunately, in many cases, learning can be done in an asymmetric setting where states a…

Cited by 0Source ↗Scholar ↗
2024

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

Ethan Rathbun, Christopher Amato, Alina Oprea
NeurIPS 2024poster

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work we explore a particularly stealthy form of training-time atta…

Cited by 2Source ↗PDF ↗Scholar ↗
2023

Equivariant Reinforcement Learning under Partial Observability

Hai Huu Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato
CoRL 2023poster

Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivarianc…

Cited by 15Source ↗Scholar ↗
2023

Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning

Brett Daley, Martha White, Christopher Amato, Marlos C. Machado
ICML 2023poster

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision manner: past temporal-difference errors are re-weighted by th…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2022

A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning

Xueguang Lyu, Andrea Baisero, Yuchen Xiao, Christopher Amato
AAAI 2022technical

Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with state-based critics, since centralized training allows access…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2022

Asymmetric DQN for partially observable reinforcement learning

Andrea Baisero, Brett Daley, Christopher Amato
UAI 2022poster

Offline training in simulated partially observable environments allows reinforcement learning methods to exploit privileged state information through a mechanism known as asymmetry. Such privileged information has the potential to greatly improve the optimal convergence properties, if used appropria…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2022

Leveraging Fully Observable Policies for Learning under Partial Observability

Hai Huu Nguyen, Andrea Baisero, Dian Wang, Christopher Amato, Robert Platt
CoRL 2022poster

Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that us…

Cited by 31Source ↗code ↗Scholar ↗
2022

Shield Decentralization for Safe Multi-Agent Reinforcement Learning

Daniel Melcer, Christopher Amato, Stavros Tripakis
NeurIPS 2022accept

Learning safe solutions is an important but challenging problem in multi-agent reinforcement learning (MARL). Shielded reinforcement learning is one approach for preventing agents from choosing unsafe actions. Current shielded reinforcement learning methods for MARL make strong assumptions about com…

Cited by 20Source ↗PDF ↗Scholar ↗
2021

End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning

Mohammadreza Sharif, Deniz Erdogmus, Christopher Amato, Taskin Padir
ICRA 2021poster

State-of-the-art human-in-the-loop robot grasping is hugely suffered by Electromyography (EMG) inference robustness issues. As a workaround, researchers have been looking into integrating EMG with other signals, often in an ad hoc manner. In this paper, we are presenting a method for end-to-end trai…

Cited by 4Source ↗code ↗Scholar ↗
2020

Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability

Hai Nguyen, Brett Daley, Xinchao Song, Christopher Amato, Robert Platt
CoRL 2020

Many important robotics problems are partially observable where a single visual or force-feedback measurement is insufficient to reconstruct the state. Standard approaches involve learning a policy over beliefs or observation-action histories. However, both of these have drawbacks; it is expensive t

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2020

Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net

Yuchen Xiao, Joshua Hoffman, Tian Xia, Christopher Amato
ICRA 2020poster

In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning decentralized policies because of the environment appearing to be…

Cited by 39Source ↗Scholar ↗
2020

To Ask or Not to Ask: A User Annoyance Aware Preference Elicitation Framework for Social Robots

Balint Gucsi, Danesh S. Tarapore, William Yeoh, Christopher Amato, Long Tran-Thanh
IROS 2020poster

In this paper we investigate how social robots can efficiently gather user preferences without exceeding the allowed user annoyance threshold. To do so, we use a Gazebo based simulated office environment with a TIAGo Steel robot. We then formulate the user annoyance aware preference elicitation prob…

Cited by 6Source ↗Scholar ↗
2019

Online Planning for Target Object Search in Clutter under Partial Observability

Yuchen Xiao, Sammie Katt, Andreas ten Pas, Shengjian Chen, Christopher Amato
ICRA 2019poster

The problem of finding and grasping a target object in a cluttered, uncertain environment, target object search, is a common and important problem in robotics. One key challenge is the uncertainty of locating and recognizing each object in a cluttered environment due to noisy perception and occlusio…

Cited by 89Source ↗Scholar ↗
2018

Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems

Trong Nghia Hoang, Yuchen Xiao, Kavinayan Sivakumar, Christopher Amato, Jonathan P. Howl
ICRA 2018poster

A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small…

Cited by 16Source ↗Scholar ↗
2017

Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability

Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian
ICML 2017poster

Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized polic…

Cited by 706Source ↗PDF ↗Scholar ↗
2017

Learning for multi-robot cooperation in partially observable stochastic environments with macro-actions

Miao Liu, Kavinayan Sivakumar, Shayegan Omidshafiei, Christopher Amato, Jonathan P. How
IROS 2017poster

This paper presents a data-driven approach for multi-robot coordination in partially-observable domains based on Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) and macro-actions (MAs). Dec-POMDPs provide a general framework for cooperative sequential decision making under…

Cited by 42Source ↗Scholar ↗
2017

Scalable accelerated decentralized multi-robot policy search in continuous observation spaces

Shayegan Omidshafiei, Christopher Amato, Miao Liu, Michael Everett, Jonathan P. How, John Vian
ICRA 2017poster

This paper presents the first ever approach for solving continuous-observation Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) and their semi-Markovian counterparts, Dec-POSMDPs. This contribution is especially important in robotics, where a vast number of sensors provide c…

Cited by 9Source ↗Scholar ↗
2017

Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations

Shayegan Omidshafiei, Shih-Yuan Liu, Michael Everett, Brett T. Lopez, Christopher Amato, Miao Liu +2
ICRA 2017poster

Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerom-eter data), bu…

Cited by 10Source ↗Scholar ↗
2016

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, John Vian
ICRA 2016

This paper introduces a probabilistic algorithm for multi-robot decision-making under uncertainty, which can be posed as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP). Dec-POMDPs are inherently synchronous decision-making frameworks which require significant computational

Cited by 23Source ↗Scholar ↗
2015

Decentralized control of Partially Observable Markov Decision Processes using belief space macro-actions

Shayegan Omidshafiei, Ali-akbar Agha-mohammadi, Christopher Amato, Jonathan P. How
ICRA 2015poster

The focus of this paper is on solving multi-robot planning problems in continuous spaces with partial observability. Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) are general models for multi-robot coordination problems, but representing and solving Dec-POMDPs is often in…

Cited by 85Source ↗Scholar ↗
2015

Planning for decentralized control of multiple robots under uncertainty

Christopher Amato, George Konidaris, Gabriel Cruz, Christopher A. Maynor, Jonathan P. How, Leslie P. Kaelbling
ICRA 2015poster

This paper presents a probabilistic framework for synthesizing control policies for general multi-robot systems that is based on decentralized partially observable Markov decision processes (Dec-POMDPs). Dec-POMDPs are a general model of decision-making where a team of agents must cooperate to optim…

Cited by 139Source ↗Scholar ↗
2015

Policy Search for Multi-Robot Coordination under Uncertainty

Christopher Amato, George Konidaris, Ariel Anders, Gabriel Cruz, Jonathan How, Leslie Kaelbling
RSS 2015poster

We introduce a principled method for multi-robot coordination based on a generic model (termed a MacDec-POMDP) of multi-robot cooperative planning in the presence of stochasticity, uncertain sensing and communication limitations. We present a new MacDec-POMDP planning algorithm that searches over po…

Cited by 101Source ↗PDF ↗Scholar ↗