English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Object Rearrangement is to move objects from an initial state to a goalstate. Here, we focus on a more practical setting in object rearrangement,i.e., rearranging objects from shuffled layouts to a normative targetdistribution without explicit goal specification. However, it remainschallenging for AI agents, as it is hard to describe the target distribution(goal specification) for reward engineering or collect expert trajectories asdemonstrations. Hence, it is infeasible to directly employ reinforcementlearning or imitation learning algorithms to address the task. This paper aimsto search for a policy only with a set of examples from a target distributioninstead of a handcrafted reward function. We employ the score-matchingobjective to train a Target Gradient Field (TarGF), indicating a direction oneach object to increase the likelihood of the target distribution. For objectrearrangement, the TarGF can be used in two ways: 1) For model-based planning,we can cast the target gradient into a reference control and output actionswith a distributed path planner; 2) For model-free reinforcement learning, theTarGF is not only used for estimating the likelihood-change as a reward butalso provides suggested actions in residual policy learning. Experimentalresults in ball and room rearrangement demonstrate that our methodsignificantly outperforms the state-of-the-art methods in the quality of theterminal state, the efficiency of the control process, and scalability.

TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification