2k citations · 2.2k across the 36 of their papers we have counts for
5 papers · 1 filter
Observation Space Matters: Benchmark and Optimization Algorithm
Joanne Taery Kim, Sehoon Ha
Recent advances in deep reinforcement learning (deep RL) enable researchers to solve challenging control problems, from simulated environments to real-world robotic tasks. However,…
Learning Human Search Behavior from Egocentric Visual Inputs
Maks Sorokin, Wenhao Yu, Sehoon Ha +1
"Looking for things" is a mundane but critical task we repeatedly carry on in our daily life. We introduce a method to develop a human character capable of searching for a randomly…
A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning
Qian Luo, Maks Sorokin, Sehoon Ha
Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using…
Learning to be Safe: Deep RL with a Safety Critic
Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha +2
Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first a…
Learning to Walk in the Real World with Minimal Human Effort
Sehoon Ha, Peng Xu, Zhenyu Tan +2
Reliable and stable locomotion has been one of the most fundamental challenges for legged robots. Deep reinforcement learning (deep RL) has emerged as a promising method for develo…