← Search

Ingook Jang

2 accepted papers

2022

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

ICML 2022spotlight

Reconstruction-based Model-Based Reinforcement Learning (MBRL) agents, such as Dreamer, often fail to discard task-irrelevant visual distractions that are prevalent in natural scenes. In this paper, we propose a reconstruction-free MBRL agent, called DreamerPro, that can enhance robustness to distra…

2021

Stochastic Policy Optimization with Heuristic Information for Robot Learning

CoRL 2021poster

Stochastic policy-based deep reinforcement learning (RL) approaches have remarkably succeeded to deal with continuous control tasks. However, applying these methods to manipulation tasks remains a challenge since actuators of a robot manipulator require high dimensional continuous action spaces. In…

Cited by 0SourceScholar