4 papers
Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints
Hany Hamed, Abhishek Naik, Colin Bellinger +1
Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency…
Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning
Fahim Shahriar, Cheryl Wang, Alireza Azimi +5
Goal-conditioned reinforcement learning (GCRL) offers a unified way to pursue diverse tasks, yet most existing methods rely on state- or position-based goal representations that ar…
Extendable Planning via Multiscale Diffusion
Chang Chen, Hany Hamed, Doojin Baek +4
Long-horizon planning is crucial in complex environments, but diffusion-based planners like Diffuser are limited by the trajectory lengths observed during training. This creates a…
Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming
Hany Hamed, Subin Kim, Dongyeong Kim +2
Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been…