31 citations · 72 across the 22 of their papers we have counts for
22 papers
Satisficing Exploration for Deep Reinforcement Learning
Dilip Arumugam, Saurabh Kumar, Ramki Gummadi +1
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environme…
Exploration Unbound
Dilip Arumugam, Wanqiao Xu, Benjamin Van Roy
A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environm…
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Akash Velu, Skanda Vaidyanath, Dilip Arumugam
Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme…
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Wanqiao Xu, Shi Dong, Dilip Arumugam +1
A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward mode…
Bayesian Reinforcement Learning with Limited Cognitive Load
Dilip Arumugam, Mark K. Ho, Noah D. Goodman +1
All biological and artificial agents must learn and make decisions given limits on their ability to process information. As such, a general theory of adaptive behavior should be ab…
Inclusive Artificial Intelligence
Dilip Arumugam, Shi Dong, Benjamin Van Roy
Prevailing methods for assessing and comparing generative AIs incentivize responses that serve a hypothetical representative individual. Evaluating models in these terms presumes h…
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning
Dilip Arumugam, Mark K. Ho, Noah D. Goodman +1
Throughout the cognitive-science literature, there is widespread agreement that decision-making agents operating in the real world do so under limited information-processing capabi…
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
Dilip Arumugam, Satinder Singh
The Bayes-Adaptive Markov Decision Process (BAMDP) formalism pursues the Bayes-optimal solution to the exploration-exploitation trade-off in reinforcement learning. As the computat…
Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning
Dilip Arumugam, Benjamin Van Roy
The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment. Recent empirical…
Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
Dilip Arumugam, Benjamin Van Roy
The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment. Recent empirical…
The Value of Information When Deciding What to Learn
Dilip Arumugam, Benjamin Van Roy
All sequential decision-making agents explore so as to acquire knowledge about a particular target. It is often the responsibility of the agent designer to construct this target wh…
Bad-Policy Density: A Measure of Reinforcement Learning Hardness
David Abel, Cameron Allen, Dilip Arumugam +3
Reinforcement learning is hard in general. Yet, in many specific environments, learning is easy. What makes learning easy in one environment, but difficult in another? We address t…
An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning
Dilip Arumugam, Peter Henderson, Pierre-Luc Bacon
How do we formalize the challenge of credit assignment in reinforcement learning? Common intuition would draw attention to reward sparsity as a key contributor to difficult credit…
Deciding What to Learn: A Rate-Distortion Approach
Dilip Arumugam, Benjamin Van Roy
Agents that learn to select optimal actions represent a prominent focus of the sequential decision-making literature. In the face of a complex environment or constraints on time an…
Randomized Value Functions via Posterior State-Abstraction Sampling
Dilip Arumugam, Benjamin Van Roy
State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms. Indeed, by exposing and accentuating various typ…
Reparameterized Variational Divergence Minimization for Stable Imitation
Dilip Arumugam, Debadeepta Dey, Alekh Agarwal +3
While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, w…
Flexible and Efficient Long-Range Planning Through Curious Exploration
Aidan Curtis, Minjian Xin, Dilip Arumugam +2
Identifying algorithms that flexibly and efficiently discover temporally-extended multi-phase plans is an essential step for the advancement of robotics and model-based reinforceme…
Deep Reinforcement Learning from Policy-Dependent Human Feedback
Dilip Arumugam, Jun Ki Lee, Sophie Saskin +1
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will ne…
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
Dilip Arumugam, David Abel, Kavosh Asadi +5
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is opti…
A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions
Siddharth Karamcheti, Edward C. Williams, Dilip Arumugam +4
Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two…
Modeling Latent Attention Within Neural Networks
Christopher Grimm, Dilip Arumugam, Siddharth Karamcheti +3
Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and int…
Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities
Dilip Arumugam, Siddharth Karamcheti, Nakul Gopalan +2
Humans can ground natural language commands to tasks at both abstract and fine-grained levels of specificity. For instance, a human forklift operator can be instructed to perform a…