Peter Stone

RLC, 2025 | Michela Proietti*, Peter R. Wurman, Peter Stone, Roberto Capobianco

The purpose of continual reinforcement learning is to train an agent on a sequence of tasks such that it learns the ones that appear later in the sequence while retaining theability to perform the tasks that appeared earlier. Experience replay is a popular method used to mak...

NEURIPS, 2025 | Michel Ma, Takuma Seno, Kaushik Subramanian, Peter R. Wurman, Peter Stone, Craig Sherstan

When designing reinforcement learning (RL) agents, a designer communicates the desired agent behavior through the definition of reward functions - numerical feedback given to the agent as reward or punishment for its actions. However, mapping desired behaviors to reward func...

ICML, 2025 | Siddhant Agarwal*, Harshit Sikchi, Peter Stone, Amy Zhang*

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as ``zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While rec...

ICML, 2025 | Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo

Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data easily leads to overfitting and unstab...

RA-L, 2025 | Hojoon Lee, Takuma Seno, Jun Jet Tai, Kaushik Subramanian, Kenta Kawamoto, Peter Stone, Peter R. Wurman

Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require instrumentation external to a car, such as precise localization of agents and opponents, limiting ...

CVPR, 2025 | Weiming Zhuang, Chen Chen, Zhizhong Li, Sina Sajadmanesh, Jingtao Li, Jiabo Huang, Vikash Sehwag, Vivek Sharma, Hirotaka Shinozaki, Felan Carlo Garcia, Yihao Zhan, Naohiro Adachi, Ryoji Eki, Michael Spranger, Peter Stone, Lingjuan Lyu

While existing vision and multi-modal foundation models can handle multiple computer vision tasks, they often suffer from significant limitations, including huge demand for data and computational resources during training and inconsistent performance across vision tasks at d...

ICLR, 2025 | Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone, Takuma Seno

Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating components that induce a simpli...

RO-MAN, 2025 | Carson Stark, Bohkyung Chun, Casey Charleston, Varsha Ravi, Luis Pabon, Surya Sunkari, Tarun Mohan, Peter Stone, Justin Hart*

This work introduces a robotics platform which embeds a conversational AI agent in an embodied system for natural language understanding and intelligent decision-making for service tasks; integrating task planning and human-like conversation. The agent is derived from a larg...

NEURIPS, 2025 | Jiaheng Hu*, Roberto Martin-Martin*, Peter Stone, Zizhao Wang*

A hallmark of intelligent agents is the ability to learn reusable skills purely from unsupervised interaction with the environment. However, existing unsupervised skill discovery methods often learn entangled skills where one skill variable simultaneously influences many ent...

NEURIPS, 2025 | Zizhao Wang*, Jiaheng Hu*, Roberto Martin-Martin*, Amy Zhang*, Scott Niekum*, Peter Stone, Caleb Chuck, Stephen Chen

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover divers...

NEURIPS, 2025 | Caroline Wang*, Arrasy Rahman*, Ishan Durugkar, Elad Liebman*, Peter Stone

Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls all agents in the scenario, while in ad hoc teamwork, the learning algor...

CORL, 2025 | Jiaheng Hu*, Peter Stone, Roberto Martin-Martin*, Ben Abbatematteo, Shivin Dass

Many robot manipulation tasks require active or interactive exploration behavior in order to be performed successfully. Such tasks are ubiquitous in embodied domains, where agents must actively search for the information necessary for each stage of a task, e.g., moving the h...

EMNLP, 2025 | Zifan Xu*, Peter Stone, Dmitriy Bespalov, Haozhu Wang, Xian Wu, Yanjun Qi

Chain-of-thought (CoT) prompting is a popularin-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL approaches construct prompts using examples that contain questions similar to the input questio...

NEURIPS, 2024 | Caroline Wang*, Arrasy Rahman*, Ishan Durugkar, Elad Liebman*, Peter Stone

Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls all agents in the scenario, while in ad hoc teamwork, the learning algor...

NEURIPS, 2024 | Borja G. Leon*, Francesco Riccio, Kaushik Subramanian, Pete Wurman, Peter Stone

The ability to approach the same problem from different angles is a cornerstone of human intelligence that leads to robust solutions and effective adaptation to problem variations. In contrast, current RL methodologies tend to lead to policies that settle on a single solutio...

RLC, 2024 | Miguel Vasco*, Takuma Seno, Kenta Kawamoto, Kaushik Subramanian, Pete Wurman, Peter Stone

Racing autonomous cars faster than the best human drivers has been a longstanding grand challenge for the fields of Artificial Intelligence and robotics. Recently, an end-to-end deep reinforcement learning agent met this challenge in a high-fidelity racing simulator, Gran Tu...

ICRA, 2024 | Haresh Karnan*, Elvin Yang*, Garrett Warnell*, Joydeep Biswas*, Peter Stone

Autonomous mobility tasks such as lastmile delivery require reasoning about operator indicated preferences over terrains on which the robot should navigate to ensure both robot safety and mission success. However, coping with out of distribution data from novel terrains or a...

COACM, 2024 | Eric Horvitz*, Vincent Conitzer*, Sheila McIlraith*, Peter Stone

Advances in artificial intelligence (AI) will transform many aspects of our lives and society, bringing immense opportunities but also posing significant risks and challenges. The next several decades may well be a turning point for humanity, comparable to the industrial rev...

AAAI, 2024 | W. Bradley Knox*, Sigurdur Orn Adalgeirsson*, Serena Booth*, Anca Dragan*, Peter Stone, Scott Niekum*

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued withi...

AAAI, 2024 | Arrasy Rahman*, Jiaxun Cui*, Peter Stone

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse tea...

ICRA, 2024 | Amir Hossain Raj*, Zichao Hu*, Haresh Karnan*, Rohan Chandra*, Amirreza Payandeh*, Luisa Mao*, Peter Stone, Joydeep Biswas*, Xuesu Xiao*

Empowering robots to navigate in a socially compliant manner is essential for the acceptance of robots moving in human-inhabited environments. Previously, roboticists have developed geometric navigation systems with decades of empirical validation to achieve safety and effic...

AR, 2024 | Alessandra Rossi*, Maike Paetzel-Prüsmann*, Merel Keijsers*, Michael Anderson*, Susan Leigh Anderson*, Daniel Barry*, Jan Gutsche*, Justin Hart*, Luca Iocchi*, Ainse Kokkelmans*, Wouter Kuijpers*, Yun Liu*, Daniel Polani*, Caleb Roscon*, Marcus Scheunemann*, Peter Stone, Florian Vahl*, René van de Molengraft*, Oskar von Stryk*

Robotics researchers have been focusing on developing autonomous and human-like intelligent robots that are able to plan, navigate, manipulate objects, and interact with humans in both static and dynamic environments. These capabilities, however, are usually developed for di...

ACC, 2024 | Catherine Weaver*, Roberto Capobianco, Peter R. Wurman, Peter Stone, Masayoshi Tomizuka*

We employ sequences of high-order motion primitives for efficient online trajectory planning, enabling competitive racecar control even when the car deviates from an offline demonstration. Dynamic Movement Primitives (DMPs) utilize a target-driven non-linear differential equ...

AAAI, 2024 | Zizhao Wang*, Caroline Wang*, Xuesu Xiao*, Yuke Zhu*, Peter Stone

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is ...

AAAI, 2024 | Arrasy Rahman*, Jiaxun Cui*, Peter Stone

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse tea...

AAAI, 2024 | W. Bradley Knox*, Stephane Hatgis-Kessell*, Sigurdur Orn Adalgeirsson*, Serena Booth*, Anca Dragan*, Peter Stone, Scott Niekum*

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments---as used in reinforcement learning from human feedback (RLHF)---including those used to fine tune ChatGPT and other contemporary language models. Most recent work o...

AAAI, 2024 | Yoonchang Sung*, Rahul Shome*, Peter Stone

This paper explores general multi-robot task and motion planning, where multiple robots in close proximity manipulate objects while satisfying constraints and a given goal. In particular, we formulate the plan refinement problem--which, given a task plan, finds valid assignm...

CMMR, 2023 | Juan M. Huerta*, Bo Liu*, Peter Stone

Automatically varying the number of notes in symbolic music has various applications in assisting music creators to embellish simple tunes or to reduce complex music to its core idea. In this paper, we formulate the problem of varying the number of notes while preserving the...

NEURIPS, 2023 | Bo Liu*, Yifeng Zhu*, Chongkai Gao*, Yihao Feng*, Qiang Liu*, Yuke Zhu*, Peter Stone

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and conce...

NEURIPS, 2023 | Bo Liu*, Yihao Feng*, Peter Stone, Qiang Liu*

One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL). However, gradient descent (GD) on the average loss across all tasks may yield poor multitask performance due to severe...

NEURIPS, 2023 | Zizhao Wang*, Jiaheng Hu*, Roberto Martin-Martin*, Peter Stone

Tasks with large state space and sparse reward present a longstanding challenge to reinforcement learning. In these tasks, an agent needs to explore the state space efficiently until it finds reward: the hard exploration problem. To deal with this problem, the community has ...

NEURIPS, 2023 | Siddhant Agarwal*, Ishan Durugkar, Amy Zhang*, Peter Stone

Goal-Conditioned RL problems provide sparse rewards where the agent receives a reward signal only when it has achieved the goal, making exploration a difficult problem. Several works augment this sparse reward with a learned dense reward function, but this can lead to subopt...

IROS, 2023 | Keya Ghonasgi*, Reuth Mirsky*, Adrian M Haith*, Peter Stone, Ashish D Deshpande*

Exoskeleton robots are capable of safe torque-controlled interactions with a wearer while moving their limbs through pre-defined trajectories. However, affecting and assisting the wearer's movements while incorporating their inputs (effort and movements) effectively during a...

IROS, 2023 | Xiaohan Zhang*, Yifeng Zhu*, Yan Ding*, Yuqian Jiang*, Yuke Zhu*, Peter Stone, Shiqi Zhang*

In existing task and motion planning (TAMP) research, it is a common assumption that experts manually specify the state space for task-level planning. A well-developed state space enables the desirable distribution of limited computational resources between task planning and...

COLLAS, 2023 | Varun Kompella, Thomas Walsh, Samuel Barrett, Peter R. Wurman, Peter Stone

Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), whi...

UAI, 2023 | Dustin Morrill, Thomas Walsh, Daniel Hernandez, Peter R. Wurman, Peter Stone

Modern reinforcement learning systems produce many high-quality policies throughout the learning process. However, to choose which policy to actually deploy in the real world, they must be tested under an intractable number of environmental conditions. We introduce RPOSST, a...

COLLAS, 2023 | Zifan Xu*, Yulin Zhang*, Shahaf S. Shperberg*, Reuth Mirsky*, Yuqian Jiang*, Bo Liu*, Peter Stone

Curriculum learning (CL) has been widely explored to facilitate the learning of hard-exploration tasks in reinforcement learning (RL) by training a sequence of easier tasks, often called a curriculum. While most curricula are built either manually or automatically based on h...

SCIENCE, 2023 | Peter R. Wurman, Peter Stone, Michael Spranger

Games continue to drive progress in the development of artificial intelligence.

RSS, 2023 | Jiaheng Hu*, Peter Stone, Roberto Martin-Martin*

Developing the next generation of household robot helpers requires combining locomotion and interaction capabilities, which is generally referred to as mobile manipulation (MoMa). MoMa tasks are difficult due to the large action space of the robot and the common multi-objec...

TAS, 2023 | Elliott Hauser*, Yao-Cheng Chan*, Geethika Hemkumar*, Daksh Dua*, Parth Chonkar*, Efren Mendoza Enriquez*, Tiffany Kao*, Shikhar Gupta*, Huihai Wang*, Justin Hart*, Reuth Mirsky*, Joydeep Biswas*, Junfeng Jiao*, Peter Stone

Autonomous service robots in a public setting will generate hundreds of incidental human-robot encounters, yet researchers have only recently addressed this important topic in earnest. In this study, we hypothesized that visual indicators of human control, such as a leash on...

ICAPS, 2023 | Vaibhav Bajaj*, Guni Sharon*, Peter Stone

Applying reinforcement learning (RL) to sparse reward domains is notoriously challenging due to insufficient guiding signals. Common RL techniques for addressing such domains include (1) learning from demonstrations and (2) curriculum learning. While these two approaches ha...

SCIENTIFIC REPORTS, 2023 | Keya Ghonasgi*, Reuth Mirsky*, Nisha Bhargava*, Adrian M Haith*, Peter Stone, Ashish D Deshpande*

Human–exoskeleton interactions have the potential to bring about changes in human behavior for physical rehabilitation or skill augmentation. Despite signifcant advances in the design and control of these robots, their application to human training remains limited. The key o...

AAMAS, 2023 | Caroline Wang*, Garrett Warnell*, Peter Stone

While combining imitation learning (IL) and reinforcement learning (RL) is a promising way to address poor sample efficiency in autonomous behavior acquisition, methods that do so typically assume that the requisite behavior demonstrations are provided by an expert that be...

ICLR, 2023 | Jiaxun Cui*, Xiaomeng Yang*, Mulong Luo*, Geunbae Lee*, Peter Stone, Hsien-Hsin S. Lee*, Benjamin Lee*, G. Edward Suh*, Wenjie Xiong*, Yuandong Tian*

Security vulnerabilities in computer systems raise serious concerns as computers process an unprecedented amount of private and sensitive data today. Cachetiming attacks (CTA) pose an important practical threat as they can effectively breach many protection mechanisms in t...

ICRA, 2023 | Jin-Soo Park*, Xuesu Xiao*, Garrett Warnell*, Harel Yedidsion*, Peter Stone

While current systems for autonomous robot navigation can produce safe and efficient motion plans in static environments, they usually generate suboptimal behaviors when multiple robots must navigate together in confined spaces. For example, when two robots meet each other i...

ICRA, 2023 | Zifan Xu*, Bo Liu*, Xuesu Xiao*, Anirudh Nair*, Peter Stone

Deep reinforcement learning (RL) has broughtmany successes for autonomous robot navigation. However,there still exists important limitations that prevent real-worlduse of RL-based navigation systems. For example, most learningapproaches lack safety guarantees; and learned na...

NEURAL NETWORKS, 2023 | Megan M. Baker*, Alexander New*, Mario Aguilar-Simon*, Ziad Al-Halah*, Sébastien M. R. Arnold*, Ese Ben-Iwhiwhu*, Andrew P. Brna*, Ethan Brooks*, Ryan C. Brown*, Zachary Daniels*, Anurag Daram*, Fabien Delattre*, Ryan Dellana*, Eric Eaton*, Haotian Fu*, Kristen Grauman*, Jesse Hostetler*, Shariq Iqbal*, Cassandra Kent*, Nicholas Ketz*, Soheil Kolouri*, George Konidaris*, Dhireesha Kudithipudi*, Seungwon Lee*, Michael L. Littman*, Sandeep Madireddy*, Jorge A. Mendez*, Eric Q. Nguyen*, Christine D. Piatko*, Praveen K. Pilly*, Aswin Raghavan*, Abrar Rahman*, Santhosh Kumar Ramakrishnan*, Neale Ratzlaff*, Andrea Soltoggio*, Peter Stone, Indranil Sur*, Zhipeng Tang*, Saket Tiwari*, Kyle Vedder*, Felix Wang*, Zifan Xu*, Angel Yanguas-Gil*, Harel Yedidsion*, Shangqun Yu*, Gautam K. Vallabha*

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to “real world” events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and syst...

ARTIFICIAL INTELLIGENCE, 2023 | W. Bradley Knox*, Alessandro Allievi*, Holger Banzhaf*, Felix Schmitt*, Peter Stone

This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaw...

AAAI, 2023 | Serena Booth*, W. Bradley Knox*, Julie Shah*, Scott Niekum*, Peter Stone, Alessandro Allievi*

In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often sparse. For example, a true task metric might encode a reward of 1 upon success and 0 otherwise. These sparse task metrics can be hard to learn from, so in pr...

AAAI, 2023 | Bo Liu*, Yihao Feng*, Qiang Liu*, Peter Stone

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the ...

AUTONOMOUS ROBOTS, 2023 | Xiaohan Zhang*, Saeid Amiri*, Jivko Sinapov*, Jesse Thomason*, Peter Stone, Shiqi Zhang*

Robots frequently need to perceive object attributes, such as red, heavy, and empty, using multimodal exploratory behaviors, such as look, lift, and shake. One possible way for robots to do so is to learn a classifier for each perceivable attribute given an exploratory behav...

AAAI, 2023 | Caroline Wang*, Ishan Durugkar, Elad Liebman*, Peter Stone

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of distributed multi-agent learning without resorting to centralized components or explicit communic...

NEURIPS, 2022 | Bo Liu*, Mao Ye*, Stephen Wright*, Peter Stone, Qiang Liu*

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning. Conventional BO methods need to differentiate through the...

NEURIPS, 2022 | James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter R. Wurman, Peter Stone

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show ...

IROS, 2022 | Keya Ghonasgi*, Reuth Mirsky*, Adrian M Haith*, Peter Stone, Ashish D Deshpande*

While human-robot interaction studies are becoming more common, quantification of the effects of repeated interaction with an exoskeleton remains unexplored. We draw upon existing literature in human skill assessment and present extrinsic and intrinsic performance metrics t...

IJCAI, 2022 | Ghada Sokar, Elena Mocanu, Decebal Constantin Mocanu, Mykola Pechenizkiy, Peter Stone

Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and memory resources are consumed. Recentl...

NATURE, 2022 | Pete Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, Hao Chih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead Amago, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano

Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block...

IJCAI, JAIR, 2021 | Jesse Thomason*, Aishwarya Padmakumar*, Jivko Sinapov*, Nick Walker*, Yuqian Jiang*, Harel Yedidsion*, Justin Hart*, Peter Stone, Raymond J. Mooney*

In this work, we present methods for using human-robot dialog to improve language understanding for a mobile robot agent. The agent parses natural language to underlying semantic meanings and uses robotic sensors to create multi-modal models of perceptual concepts like red a...

JAIR, 2021 | Roberto Capobianco, Varun Kompella, James Ault*, Guni Sharon*, Stacy Jong*, Spencer Fox*, Lauren Meyers*, Pete Wurman, Peter Stone

The year 2020 saw the covid-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world have been faced with the challenge of protecting public health while keeping the economy running to the greatest extent possible. Epidemiologi...

ICRA, 2021 | Piyush Khandelwal, James MacGlashan, Pete Wurman, Peter Stone

It has been recently demonstrated that Temporal Convolution Networks (TCNs) provide state-of-the-art results in many problem domains where the input data is a time-series. TCNs typically incorporate information from a long history of inputs (the receptive field) into a singl...

AAMAS, 2021 | Guni Sharon*, James Ault*, Peter Stone, Varun Kompella, Roberto Capobianco

This paper addresses an epidemiologic inference problem where, given realtime observation of test results, presence of symptoms,and physical contacts, the most likely infected individuals need to be inferred. The inference problem is modeled as a hidden Markovmodel where inf...

AAAI, 2021 | William Macke*, Reuth Mirsky*, Peter Stone

A desirable goal for autonomous agents is to be able to coordinate on the fly with previously unknown teammates. Known as "ad hoc teamwork", enabling such a capability has been receiving increasing attention in the research community. One of the central challenges in ad hoc ...

AAAI, 2021 | Yuqian Jiang*, Sudarshanan Bharadwaj*, Bo Wu*, Rishi Shah*, Ufuk Topcu*, Peter Stone

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward...

AAAI, 2021 | Yu-Sian Jiang*, Garrett Warnell*, Peter Stone

Human-robot shared autonomy techniques for vehicle navigation hold promise for reducing a human driver's workload, ensuring safety, and improving navigation efficiency. However, because typical techniques achieve these improvements by effectively removing human control at cr...

IJCAI, 2021 | Reuth Mirsky*, William Macke*, Andy Wang*, Harel Yedidsion*, Peter Stone

In ad hoc teamwork, multiple agents need to collaborate without having knowledge about their teammates or their plans a priori. A common assumption in this research area is that the agents cannot communicate. However, just as two random people may speak the same language, au...

IJCAI, 2021 | Ishan Durugkar, Elad Liebman*, Peter Stone

In multiagent reinforcement learning scenarios, it is often the case that independent agents must jointly learn to perform a cooperative task. This paper focuses on such a scenario in which agents have individual preferences regarding how to accomplish the shared task. We co...

NEURIPS, 2020 | Lemeng Wu*, Bo Liu*, Peter Stone, Qiang Liu*

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best netw...

NEURIPS, 2020 | Siddharth Desai*, Ishan Durugkar, Haresh Karnan*, Garrett Warnell*, Josiah Hanna*, Peter Stone

We examine the problem of transferring a policy learned in a source environment to a target environment with different dynamics, particularly in the case where it is critical to reduce the amount of interaction with the target environment during learning. This problem is par...

AAAI AI FOR SOCIAL GOOD, 2020 | Varun Kompella, Roberto Capobianco, Stacy Jong*, Jonathan Browne*, Spencer Fox*, Lauren Meyers*, Pete Wurman, Peter Stone

The year 2020 has seen the COVID-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world are faced with the challenge of protecting public health, while keeping the economy running to the greatest extent possible. Epidemiologi...