Alert button
Picture for Dilip Arumugam

Dilip Arumugam

Alert button

Social Contract AI: Aligning AI Assistants with Implicit Group Norms

Oct 26, 2023
Jan-Philipp Fränken, Sam Kwok, Peixuan Ye, Kanishk Gandhi, Dilip Arumugam, Jared Moore, Alex Tamkin, Tobias Gerstenberg, Noah D. Goodman

Viaarxiv icon

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

Jul 21, 2023
Akash Velu, Skanda Vaidyanath, Dilip Arumugam

Figure 1 for Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Figure 2 for Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Figure 3 for Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Figure 4 for Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Viaarxiv icon

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

May 19, 2023
Wanqiao Xu, Shi Dong, Dilip Arumugam, Benjamin Van Roy

Figure 1 for Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Figure 2 for Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Figure 3 for Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Figure 4 for Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Viaarxiv icon

Bayesian Reinforcement Learning with Limited Cognitive Load

May 05, 2023
Dilip Arumugam, Mark K. Ho, Noah D. Goodman, Benjamin Van Roy

Figure 1 for Bayesian Reinforcement Learning with Limited Cognitive Load
Figure 2 for Bayesian Reinforcement Learning with Limited Cognitive Load
Figure 3 for Bayesian Reinforcement Learning with Limited Cognitive Load
Figure 4 for Bayesian Reinforcement Learning with Limited Cognitive Load
Viaarxiv icon

Inclusive Artificial Intelligence

Dec 24, 2022
Dilip Arumugam, Shi Dong, Benjamin Van Roy

Figure 1 for Inclusive Artificial Intelligence
Viaarxiv icon

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

Oct 30, 2022
Dilip Arumugam, Mark K. Ho, Noah D. Goodman, Benjamin Van Roy

Viaarxiv icon

Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction

Oct 30, 2022
Dilip Arumugam, Satinder Singh

Viaarxiv icon

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

Jun 04, 2022
Dilip Arumugam, Benjamin Van Roy

Viaarxiv icon

Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning

Jun 04, 2022
Dilip Arumugam, Benjamin Van Roy

Viaarxiv icon

The Value of Information When Deciding What to Learn

Oct 26, 2021
Dilip Arumugam, Benjamin Van Roy

Figure 1 for The Value of Information When Deciding What to Learn
Figure 2 for The Value of Information When Deciding What to Learn
Viaarxiv icon