activity
20192022
most citedLearning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning

45 citations · 87 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG202217 cited

Subverting machines, fluctuating identities: Re-learning human categorization

Christina Lu, Jackie Kay, Kevin R. McKee

Most machine learning systems that interact with humans construct some notion of a person's "identity," yet the default paradigm in AI research envisions identity with essential at…

cs.LG2020

Local Search for Policy Iteration in Continuous Control

Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz +10

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framew…

cs.RO2020

Learning Dexterous Manipulation from Suboptimal Experts

Rae Jeong, Jost Tobias Springenberg, Jackie Kay +5

Learning dexterous manipulation in high-dimensional state-action spaces is an important open challenge with exploration presenting a major bottleneck. Although in many cases the le…

cs.RO201916 cited

Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer

Rae Jeong, Jackie Kay, Francesco Romano +6

Learning robotic control policies in the real world gives rise to challenges in data efficiency, safety, and controlling the initial condition of the system. On the other hand, sim…

cs.RO20199 cited

Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation

Rae Jeong, Yusuf Aytar, David Khosid +5

Collecting and automatically obtaining reward signals from real robotic visual data for the purposes of training reinforcement learning algorithms can be quite challenging and time…

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…