no code implementations • 11 Apr 2024 • Shang Wang, Deepak Ranganatha Sastry Mamillapalli, Tianpei Yang, Matthew E. Taylor
This paper introduces the problem of learning to place logic blocks in Field-Programmable Gate Arrays (FPGAs) and a learning-based method.
1 code implementation • 9 Feb 2024 • Simone Parisi, Montaser Mohammedalamen, Alireza Kazemipour, Matthew E. Taylor, Michael Bowling
In this paper, we formalize a novel but general RL framework - Monitored MDPs - where the agent cannot always observe rewards.
no code implementations • 3 Jan 2024 • Chaitanya Kharyal, Sai Krishna Gottipati, Tanmay Kumar Sinha, Srijita Das, Matthew E. Taylor
However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors.
no code implementations • 31 Dec 2023 • Qianxi Li, Yingyue Cao, Jikun Kang, Tianpei Yang, Xi Chen, Jun Jin, Matthew E. Taylor
Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance.
1 code implementation • 23 Dec 2023 • Bram Grooten, Tristan Tomilin, Gautham Vasan, Matthew E. Taylor, A. Rupam Mahmood, Meng Fang, Mykola Pechenizkiy, Decebal Constantin Mocanu
Our algorithm improves the agent's focus with useful masks, while its efficient Masker network only adds 0. 2% more parameters to the original structure, in contrast to previous work.
no code implementations • 19 Dec 2023 • Rupali Bhati, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor
While there has been significant progress in curriculum learning and continuous learning for training agents to generalize across a wide variety of environments in the context of single-agent reinforcement learning, it is unclear if these algorithms would still be valid in a multi-agent setting.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 18 Dec 2023 • Laila El Moujtahid, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor
With this platform, we hope to facilitate further research on human-machine teaming in critical systems and defense environments.
no code implementations • 1 Nov 2023 • Afia Abedin, Abdul Bais, Cody Buntain, Laura Courchesne, Brian McQuinn, Matthew E. Taylor, Muhib Ullah
The massive proliferation of social media data represents a transformative moment in conflict studies.
1 code implementation • 10 Jul 2023 • Fatemeh Abdollahi, Saqib Ameen, Matthew E. Taylor, Levi H. S. Lelis
Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines.
no code implementations • NeurIPS 2023 • Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman
We propose \textit{information gating} as a way to learn parsimonious representations that identify the minimal information required for a task.
1 code implementation • 13 Feb 2023 • Bram Grooten, Ghada Sokar, Shibhansh Dohare, Elena Mocanu, Matthew E. Taylor, Mykola Pechenizkiy, Decebal Constantin Mocanu
Tomorrow's robots will need to distinguish useful information from noise when performing different tasks.
1 code implementation • 26 Jan 2023 • Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley
This paper considers the problem of simultaneously learning from multiple independent advisors in multi-agent reinforcement learning.
no code implementations • 16 Dec 2022 • Hager Radi, Josiah P. Hanna, Peter Stone, Matthew E. Taylor
In our setting, we assume a source of data, which we split into a train-set, to learn an offline policy, and a test-set, to estimate a lower-bound on the offline policy using off-policy evaluation with bootstrapping.
no code implementations • 14 Nov 2022 • Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
no code implementations • 13 Oct 2022 • Michael Guevarra, Srijita Das, Christabel Wayllace, Carrie Demmans Epp, Matthew E. Taylor, Alan Tay
We propose an AI-based pilot trainer to help students learn how to fly aircraft.
no code implementations • 25 Apr 2022 • Alex Lewandowski, Calarina Muslimani, Dale Schuurmans, Matthew E. Taylor, Jun Luo
To effectively learn such a teaching policy, we introduce a parametric-behavior embedder that learns a representation of the student's learnable parameters from its input/output behavior.
no code implementations • 14 Apr 2022 • Sahir, Ercüment İlhan, Srijita Das, Matthew E. Taylor
Reinforcement learning (RL) has shown great success in solving many challenging tasks via use of deep neural networks.
1 code implementation • 16 Mar 2022 • Pengyi Li, Hongyao Tang, Tianpei Yang, Xiaotian Hao, Tong Sang, Yan Zheng, Jianye Hao, Matthew E. Taylor, Wenyuan Tao, Zhen Wang, Fazl Barez
However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 15 Nov 2021 • Manan Tomar, Utkarsh A. Mishra, Amy Zhang, Matthew E. Taylor
A wide range of methods have been proposed to enable efficient learning, leading to sample complexities similar to those in the full state setting.
1 code implementation • 26 Oct 2021 • Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley
In the last decade, there have been significant advances in multi-agent reinforcement learning (MARL) but there are still numerous challenges, such as high sample complexity and slow convergence to stable policies, that need to be overcome before wide-spread deployment is possible.
no code implementations • 29 Sep 2021 • Manan Tomar, Amy Zhang, Matthew E. Taylor
The common representation acts as a implicit invariance objective to avoid the different spurious correlations captured by individual predictors.
1 code implementation • 11 Apr 2021 • Brittany Davis Pierson, Justine Ventura, Matthew E. Taylor
Reinforcement learning has made great strides in recent years due to the success of methods using deep neural networks.
no code implementations • 7 Mar 2021 • Volodymyr Tkachuk, Sriram Ganapathi Subramanian, Matthew E. Taylor
We aim to bridge the gap between theoretical and empirical work in $Q$-function reuse by providing some theoretical insights on the effectiveness of $Q$-function reuse when applied to the $Q$-learning with UCB-Hoeffding algorithm.
no code implementations • ICLR Workshop SSL-RL 2021 • Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau
Unlike previous forms of state abstractions, a model-invariance state abstraction leverages causal sparsity over state variables.
no code implementations • 15 Feb 2021 • Yaodong Yang, Jun Luo, Ying Wen, Oliver Slumbers, Daniel Graves, Haitham Bou Ammar, Jun Wang, Matthew E. Taylor
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games.
no code implementations • 2 Feb 2021 • Matthew E. Taylor, Nicholas Nissen, YuAn Wang, Neda Navidi
OpenAI Gym is a common framework for RL research, including a large number of standard environments and agents, making RL research significantly more accessible.
1 code implementation • 18 Jan 2021 • Nikunj Gupta, G Srinivasaraghavan, Swarup Kumar Mohalik, Nishant Kumar, Matthew E. Taylor
This paper considers the case where there is a single, powerful, \emph{central agent} that can observe the entire observation space, and there are multiple, low-powered \emph{local agents} that can only receive local observations and are not able to communicate with each other.
Multi-agent Reinforcement Learning reinforcement-learning +2
1 code implementation • 31 Dec 2020 • Sriram Ganapathi Subramanian, Matthew E. Taylor, Mark Crowley, Pascal Poupart
Traditional multi-agent reinforcement learning algorithms are not scalable to environments with more than a few agents, since these algorithms are exponential in the number of agents.
Multi-agent Reinforcement Learning Q-Learning Multiagent Systems
no code implementations • 2 Nov 2020 • Paniz Behboudian, Yash Satsangi, Matthew E. Taylor, Anna Harutyunyan, Michael Bowling
Furthermore, if the reward is constructed from a potential function, the optimal policy is guaranteed to be unaltered.
1 code implementation • 8 Oct 2020 • Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon).
1 code implementation • 29 Sep 2020 • Yunshu Du, Garrett Warnell, Assefaw Gebremedhin, Peter Stone, Matthew E. Taylor
In this work, we introduce Lucid Dreaming for Experience Replay (LiDER), a conceptually new framework that allows replay experiences to be refreshed by leveraging the agent's current policy.
no code implementations • 3 Jul 2020 • Adam Bignold, Francisco Cruz, Matthew E. Taylor, Tim Brys, Richard Dazeley, Peter Vamplew, Cameron Foale
In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process.
no code implementations • 1 Apr 2020 • Craig Sherstan, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
Our overall conclusions are that TD-AE increases the robustness of the A2C algorithm to the trajectory length and while promising, further study is required to fully understand the relationship between auxiliary task prediction timescale and the agent's performance.
no code implementations • 10 Mar 2020 • Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, Peter Stone
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback.
1 code implementation • 6 Feb 2020 • Sriram Ganapathi Subramanian, Pascal Poupart, Matthew E. Taylor, Nidhi Hegde
We consider two different kinds of mean field environments: a) Games where agents belong to predefined types that are known a priori and b) Games where the type of each agent is unknown and therefore must be learned based on observations.
no code implementations • 26 Jul 2019 • Chao Gao, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
In this paper, we illuminate reasons behind this failure by providing a thorough analysis on the hardness of random exploration in Pommerman.
no code implementations • 25 Jul 2019 • Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency.
no code implementations • 24 Jul 2019 • Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
Deep reinforcement learning has achieved great successes in recent years, but there are still open challenges, such as convergence to locally optimal policies and sample inefficiency.
no code implementations • 22 Jul 2019 • Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling.
no code implementations • 19 Jul 2019 • Robert Loftin, Bei Peng, Matthew E. Taylor, Michael L. Littman, David L. Roberts
In order for robots and other artificial agents to efficiently learn to perform useful tasks defined by an end user, they must understand not only the goals of those tasks, but also the structure and dynamics of that user's environment.
1 code implementation • 20 Apr 2019 • Chao Gao, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
The Pommerman Team Environment is a recently proposed benchmark which involves a multi-agent domain with challenges such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards.
no code implementations • 10 Apr 2019 • Bilal Kartal, Pablo Hernandez-Leal, Chao GAO, Matthew E. Taylor
In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic events (i. e., suicides) that happen under random exploration in this domain.
1 code implementation • 3 Apr 2019 • Gabriel V. de la Cruz Jr., Yunshu Du, Matthew E. Taylor
Deep Reinforcement Learning (DRL) algorithms are known to be data inefficient.
1 code implementation • 21 Dec 2018 • Gabriel V. de la Cruz, Yunshu Du, Matthew E. Taylor
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images.
no code implementations • 30 Nov 2018 • Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor
Deep reinforcement learning (DRL) has achieved great successes in recent years with the help of novel methods and higher compute power.
no code implementations • 17 Nov 2018 • Behzad Ghazanfari, Fatemeh Afghah, Matthew E. Taylor
Reinforcement learning (RL) techniques, while often powerful, can suffer from slow learning speeds, particularly in high dimensional spaces.
no code implementations • 12 Oct 2018 • Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor
The primary goal of this article is to provide a clear overview of current multiagent deep reinforcement learning (MDRL) literature.
no code implementations • 15 May 2018 • Ariel Rosenfeld, Moshe Cohen, Matthew E. Taylor, Sarit Kraus
However, injecting human knowledge into an RL agent may require extensive effort and expertise on the human designer's part.
no code implementations • 11 May 2018 • Zhaodong Wang, Matthew E. Taylor
This paper introduces an effective transfer approach, DRoP, combining the offline knowledge (demonstrations recorded before learning) with online confidence-based performance analysis.
no code implementations • 10 May 2018 • Kenny Young, Baoxiang Wang, Matthew E. Taylor
Finally, we apply Metatrace for control with nonlinear function approximation in 5 games in the Arcade Learning Environment where we explore how it impacts learning speed and robustness to initial step-size choice.
no code implementations • 14 Sep 2017 • Behzad Ghazanfari, Matthew E. Taylor
This paper proposes a novel practical method that can autonomously decompose tasks, by leveraging association rule mining, which discovers hidden relationship among entities in data mining.
no code implementations • 12 Sep 2017 • Gabriel V. de la Cruz Jr, Yunshu Du, Matthew E. Taylor
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images.
no code implementations • 28 Jul 2017 • Anestis Fachantidis, Matthew E. Taylor, Ioannis Vlahavas
In this article we study the transfer learning model of action advice under a budget.
no code implementations • ICML 2017 • James MacGlashan, Mark K. Ho, Robert Loftin, Bei Peng, Guan Wang, David Roberts, Matthew E. Taylor, Michael L. Littman
This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback.
no code implementations • 13 Apr 2016 • Yusen Zhan, Haitham Bou Ammar, Matthew E. Taylor
This paper formally defines a setting where multiple teacher agents can provide advice to a student and introduces an algorithm to leverage both autonomous exploration and teacher's advice.
no code implementations • 2 Jul 2015 • Yusen Zhan, Matthew E. Taylor
This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer.