ASID: Active Exploration for System Identification in Robotic Manipulation

no code implementations • 18 Apr 2024 • Marius Memmel, Andrew Wagenmaker, Chuning Zhu, Patrick Yin, Dieter Fox, Abhishek Gupta

In this work, we propose a learning system that can leverage a small amount of real-world data to autonomously refine a simulation model and then plan an accurate control strategy that can be deployed in the real world.

Transferable Reinforcement Learning via Generalized Occupancy Models

no code implementations • 10 Mar 2024 • Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta

In this work, we propose a novel class of models - generalized occupancy models (GOMs) - that retain the generality of model-based RL while avoiding compounding error.

reinforcement-learning Reinforcement Learning (RL)

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

1 code implementation • 30 Oct 2023 • Zhaoyi Zhou, Chuning Zhu, Runlong Zhou, Qiwen Cui, Abhishek Gupta, Simon Shaolei Du

Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems.

Decision Making Offline RL +1

Model-Based Reinforcement Learning via Latent-Space Collocation

1 code implementation • 24 Jun 2021 • Oleh Rybkin, Chuning Zhu, Anusha Nagabandi, Kostas Daniilidis, Igor Mordatch, Sergey Levine

The resulting latent collocation method (LatCo) optimizes trajectories of latent states, which improves over previously proposed shooting methods for visual model-based RL on tasks with sparse rewards and long-term goals.

Model-based Reinforcement Learning reinforcement-learning +1