Search Results for author: Matthew E. Taylor

Found 55 papers, 16 papers with code

Monitored Markov Decision Processes

1 code implementation9 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.

Reinforcement Learning (RL)

GLIDE-RL: Grounded Language Instruction through DEmonstration in RL

no code implementations3 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.

Continual Learning reinforcement-learning +1

LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models

no code implementations31 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.

Question Answering

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

1 code implementation23 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.

Data Augmentation

Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning

no code implementations19 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

Human-Machine Teaming for UAVs: An Experimentation Platform

no code implementations18 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.

Can You Improve My Code? Optimizing Programs with Local Search

1 code implementation10 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.

Ignorance is Bliss: Robust Control via Information Gating

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.

Inductive Bias Q-Learning

Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning

1 code implementation26 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.

Multi-agent Reinforcement Learning Q-Learning +2

Safe Evaluation For Offline Learning: Are We Ready To Deploy?

no code implementations16 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.

Off-policy evaluation

NeurIPS 2022 Competition: Driving SMARTS

no code implementations14 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.

Autonomous Driving Reinforcement Learning (RL)

Reinforcement Teaching

no code implementations25 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.

Meta-Learning

Methodical Advice Collection and Reuse in Deep Reinforcement Learning

no code implementations14 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.

Atari Games reinforcement-learning +1

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

1 code implementation16 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

Learning Representations for Pixel-based Control: What Matters and Why?

no code implementations15 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.

Contrastive Learning Representation Learning

Multi-Agent Advisor Q-Learning

1 code implementation26 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.

Decision Making Multi-agent Reinforcement Learning +3

Learning Minimal Representations with Model Invariance

no code implementations29 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.

Self-Supervised Learning

The Atari Data Scraper

1 code implementation11 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.

reinforcement-learning Reinforcement Learning (RL)

The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning

no code implementations7 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.

Q-Learning Transfer Learning

Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym

no code implementations2 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.

OpenAI Gym Reinforcement Learning (RL)

HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

1 code implementation18 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

Partially Observable Mean Field Reinforcement Learning

1 code implementation31 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

Useful Policy Invariant Shaping from Arbitrary Advice

no code implementations2 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.

Maximum Reward Formulation In Reinforcement Learning

1 code implementation8 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).

Drug Discovery reinforcement-learning +1

Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy

1 code implementation29 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.

Atari Games Reinforcement Learning (RL)

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

no code implementations3 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.

Decision Making reinforcement-learning +2

Work in Progress: Temporally Extended Auxiliary Tasks

no code implementations1 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.

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey

no code implementations10 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.

reinforcement-learning Reinforcement Learning (RL) +1

Multi Type Mean Field Reinforcement Learning

1 code implementation6 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.

reinforcement-learning Reinforcement Learning (RL) +1

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman

no code implementations26 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.

reinforcement-learning Reinforcement Learning (RL)

Action Guidance with MCTS for Deep Reinforcement Learning

no code implementations25 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.

reinforcement-learning Reinforcement Learning (RL)

Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning

no code implementations24 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.

Atari Games reinforcement-learning +2

Agent Modeling as Auxiliary Task for Deep Reinforcement Learning

no code implementations22 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.

reinforcement-learning Reinforcement Learning (RL) +1

Interactive Learning of Environment Dynamics for Sequential Tasks

no code implementations19 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.

Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition

1 code implementation20 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.

Reinforcement Learning (RL)

Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

no code implementations10 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.

reinforcement-learning Reinforcement Learning (RL) +1

Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning

1 code implementation21 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.

reinforcement-learning Reinforcement Learning (RL)

Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL

no code implementations30 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.

reinforcement-learning Reinforcement Learning (RL)

A Survey and Critique of Multiagent Deep Reinforcement Learning

no code implementations12 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.

reinforcement-learning Reinforcement Learning (RL)

Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstration

no code implementations11 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.

reinforcement-learning Reinforcement Learning (RL)

Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control

no code implementations10 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.

Atari Games Meta-Learning +1

Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multi-task Reinforcement Learning

no code implementations14 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.

reinforcement-learning Reinforcement Learning (RL)

Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning

no code implementations12 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.

Atari Games reinforcement-learning +1

Interactive Learning from Policy-Dependent Human Feedback

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.

Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer

no code implementations13 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.

reinforcement-learning Reinforcement Learning (RL) +1

Online Transfer Learning in Reinforcement Learning Domains

no code implementations2 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.

Q-Learning reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.