Dilip Arumugam

发表

Toward Good Abstractions for Lifelong Learning

M. Littman, David Abel, Dilip Arumugam, 2017 .

Modeling Latent Attention Within Neural Networks

Lawson L. S. Wong, Christopher Grimm, Michael L. Littman, 2018 .

State Abstraction as Compression in Apprenticeship Learning

Lawson L. S. Wong, Kavosh Asadi, Michael L. Littman, 2019, AAAI.

“ Structure & Priors in Reinforcement Learning ” at ICLR 2019 V ALUE P RESERVING S TATE-A CTION A BSTRACTIONS ( A PPENDIX )

Doina Precup, M. Littman, Khimya Khetarpal, 2019 .

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

B. V. Roy, Dilip Arumugam, 2022, 2206.02072.

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

B. V. Roy, Dilip Arumugam, 2022, ArXiv.

Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction

Satinder Singh, Satinder Singh, Dilip Arumugam, 2022, NeurIPS.

On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning

Noah D. Goodman, Benjamin Van Roy, Mark K. Ho, 2022, ArXiv.

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Benjamin Van Roy, B. V. Roy, Dilip Arumugam, 2022, NeurIPS.

Grounding natural language instructions to semantic goal representations for abstraction and generalization

Lawson L. S. Wong, Stefanie Tellex, Siddharth Karamcheti, 2018, Autonomous Robots.

I N THE ZONE: M EASURING DIFFICULTY AND PROGRESSION IN CURRICULUM GENERATION

Noah D. Goodman, Natasha Jaques, Dilip Arumugam, 2022 .

Inclusive Artificial Intelligence

B. V. Roy, Dilip Arumugam, Shi Dong, 2022, 2212.12633.

Value Preserving State-Action Abstractions

Doina Precup, Khimya Khetarpal, Michael L. Littman, 2020, AISTATS.

State Abstractions for Lifelong Reinforcement Learning

Michael L. Littman, Dilip Arumugam, David Abel, 2018, ICML.

Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities pdf

Stefanie Tellex, Lawson L. S. Wong, Dilip Arumugam, 2017, Robotics: Science and Systems.

Inclusive Artificial Intelligence

Benjamin Van Roy, Dilip Arumugam, Shi Dong, 2022, ArXiv.

Sequence-to-Sequence Language Grounding of Non-Markovian Task Specifications

Stefanie Tellex, Lawson L. S. Wong, Dilip Arumugam, 2018, Robotics: Science and Systems.

Bayesian Reinforcement Learning With Limited Cognitive Load

Noah D. Goodman, Benjamin Van Roy, Mark K. Ho, 2023, Open Mind.

Deep Reinforcement Learning from Policy-Dependent Human Feedback pdf

Michael L. Littman, Jun Ki Lee, Dilip Arumugam, 2019, ArXiv.

The Value of Information When Deciding What to Learn pdf

Benjamin Van Roy, Dilip Arumugam, Benjamin Van Roy, 2021, NeurIPS.

Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models

Benjamin Van Roy, Dilip Arumugam, Shi Dong, 2023, ArXiv.

Grounding English Commands to Reward Functions

Smaranda Muresan, Stefanie Tellex, Marie desJardins, 2015, Robotics: Science and Systems.

Deciding What to Learn: A Rate-Distortion Approach

Benjamin Van Roy, Dilip Arumugam, Dilip Arumugam, 2021, ICML.

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

Akash Velu, Dilip Arumugam, Skanda Vaidyanath, 2023, arXiv.org.

State Abstractions for Lifelong Reinforcement Learning

M. Littman, David Abel, Dilip Arumugam, 2018, ICML.

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning pdf

Peter Henderson, Dilip Arumugam, Pierre-Luc Bacon, 2021, ArXiv.

Reducing the Information Horizon of Bayes-Adaptive Markov Decision Processes via Epistemic State Abstraction

Dilip Arumugam, 2021 .

Grounding natural language instructions to semantic goal representations for abstraction and generalization

Stefanie Tellex, Lawson L. S. Wong, Dilip Arumugam, 2018, Auton. Robots.

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

Akash Velu, Dilip Arumugam, Skanda Vaidyanath, 2023, ArXiv.

Mitigating Planner Overfitting in Model-Based Reinforcement Learning pdf

Christopher Grimm, Kavosh Asadi, Michael L. Littman, 2018, ArXiv.

Reparameterized Variational Divergence Minimization for Stable Imitation pdf

Asli Çelikyilmaz, Debadeepta Dey, William B. Dolan, 2020, ArXiv.

Bad-Policy Density: A Measure of Reinforcement Learning Hardness pdf

Lawson L. S. Wong, Michael L. Littman, Dilip Arumugam, 2021, ArXiv.

Randomized Value Functions via Posterior State-Abstraction Sampling

Benjamin Van Roy, Dilip Arumugam, 2020, ArXiv.

A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions

Stefanie Tellex, Lawson L. S. Wong, Dilip Arumugam, 2017, RoboNLP@ACL.