activity
20172022
most citedAdversarial Attacks on Neural Network Policies

68 citations · 151 across the 6 of their papers we have counts for

collaborators

9 papers

cs.LG2022

Learning Causal Overhypotheses through Exploration in Children and Computational Models

Eliza Kosoy, Adrian Liu, Jasmine Collins +7

Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics,…

cs.AI20207 cited

Exploring Exploration: Comparing Children with RL Agents in Unified Environments

Eliza Kosoy, Jasmine Collins, David M. Chan +6

Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn. In turn, this ear…

cs.LG202024 cited

A Distributional View on Multi-Objective Policy Optimization

Abbas Abdolmaleki, Sandy H. Huang, Leonard Hasenclever +7

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for…

cs.RO20197 cited

Nonverbal Robot Feedback for Human Teachers

Sandy H. Huang, Isabella Huang, Ravi Pandya +1

Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being informative is unfortunately very challenging,…

cs.RO201945 cited

Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning

Sandy H. Huang, Martina Zambelli, Jackie Kay +4

Robots must know how to be gentle when they need to interact with fragile objects, or when the robot itself is prone to wear and tear. We propose an approach that enables deep rein…

cs.AI2018

Human-AI Learning Performance in Multi-Armed Bandits

Ravi Pandya, Sandy H. Huang, Dylan Hadfield-Menell +1

People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at…