CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
Mujoco: A physics engine for model-based control.IEEE/RSJ International Conference on Intelligent Robots and Sys- tems, pages 5026–5033
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
The work introduces behavior-invariant latent task representations via information-theoretic learning in a Transformer world model plus conservative penalties on imagined rollouts to improve generalization in offline meta-RL.
Shallow MLPs and dense CPGs outperform deeper MLPs and Actor-Critic RL in bounded robot control tasks with limited proprioception, with a Parameter Impact metric indicating extra RL parameters yield no performance gain over evolutionary strategies.
citing papers explorer
-
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
-
Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
-
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
The work introduces behavior-invariant latent task representations via information-theoretic learning in a Transformer world model plus conservative penalties on imagined rollouts to improve generalization in offline meta-RL.
-
Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization
Shallow MLPs and dense CPGs outperform deeper MLPs and Actor-Critic RL in bounded robot control tasks with limited proprioception, with a Parameter Impact metric indicating extra RL parameters yield no performance gain over evolutionary strategies.