Dilip Arumugam
Stanford University
H-index: 12
North America-United States
Top articles of Dilip Arumugam
Bayesian reinforcement learning with limited cognitive load
Open Mind
2024/4/16
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
Social Contract AI: Aligning AI Assistants with Implicit Group Norms
2023/10/26
Kanishk Gandhi
H-Index: 1
Dilip Arumugam
H-Index: 8
Jared Moore
H-Index: 6
Alex Tamkin
H-Index: 5
Tobias Gerstenberg
H-Index: 18
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
arXiv preprint arXiv:2307.11897
2023/7/21
Akash Velu
H-Index: 0
Dilip Arumugam
H-Index: 8
Shattering the agent-environment interface for fine-tuning inclusive language models
arXiv preprint arXiv:2305.11455
2023/5/19
Cultural reinforcement learning: a framework for modeling cumulative culture on a limited channel
Proceedings of the Annual Meeting of the Cognitive Science Society
2023
Ben Prystawski
H-Index: 0
Dilip Arumugam
H-Index: 8
Inclusive Artificial Intelligence
arXiv preprint arXiv:2212.12633
2022/12/24
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
Advances in Neural Information Processing Systems
2022/12/6
Dilip Arumugam
H-Index: 8
Satinder Singh
H-Index: 43
Deciding what to model: Value-equivalent sampling for reinforcement learning
Advances in Neural Information Processing Systems
2022/12/6
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning
arXiv preprint arXiv:2210.16877
2022/10/30
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
Between rate-distortion theory & value equivalence in model-based reinforcement learning
arXiv preprint arXiv:2206.02025
2022/6/4
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
In the ZONE: Measuring difficulty and progression in curriculum generation
2022
The value of information when deciding what to learn
Advances in Neural Information Processing Systems
2021/12/6
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
Bad-policy density: A measure of reinforcement learning hardness
ICML Workshop on Reinforcement Learning Theory
2021/7
Interpreting human-robot instructions
2021/8/10
Deciding what to learn: A rate-distortion approach
2021/7/1
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
Sequence-to-sequence language grounding of non-Markovian task specifications
2021/6/15
An information-theoretic perspective on credit assignment in reinforcement learning
arXiv preprint arXiv:2103.06224
2021/3/10
Dilip Arumugam
H-Index: 8
Peter Henderson
H-Index: 13
Flexible and efficient long-range planning through curious exploration
2020/11/21
Randomized value functions via posterior state-abstraction sampling
arXiv preprint arXiv:2010.02383
2020/10/5
Dilip Arumugam
H-Index: 8
Benjamin Van Roy
H-Index: 38
Reparameterized variational divergence minimization for stable imitation
arXiv preprint arXiv:2006.10810
2020/6/18
Dilip Arumugam
H-Index: 8
Co-Authors
