activity
20192026
most citedBenchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints

24 citations · 27 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

Chuhan Zhang, Seiji Ito, Kenta Hoshino +2

World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can str…