paper-with-me

홈 › Papers

Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

2019-05-01 · ICLR 2019 5 · Kenneth Marino, Abhinav Gupta, Rob Fergus, Arthur Szlam

In this paper we introduce a simple, robust approach to hierarchically training an agent in the setting of sparse reward tasks. The agent is split into a low-level and a high-level policy. The low-level policy only accesses internal, proprioceptive dimensions of the state observation. The low-level policies are trained with a simple reward that encourages changing the values of the non-proprioceptive dimensions. Furthermore, it is induced to be periodic with the use a ``phase function.'' The high-level policy is trained using a sparse, task-dependent reward, and operates by choosing which of the low-level policies to run at any given time. Using this approach, we solve difficult maze and navigation tasks with sparse rewards using the Mujoco Ant and Humanoid agents and show improvement over recent hierarchical methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

MuJoCo

Similar Papers 제목 키워드 기반

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

2020-02-01 · Zhang-Wei Hong, Prabhat Nagarajan, Guilherme Maeda

Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner bef…

Knowledge DistillationMuJoCoreinforcement-learningReinforcement Learning+1

From Simple to Complex Skills: The Case of In-Hand Object Reorientation

2025-01-09 · Haozhi Qi, Brent Yi, Mike Lambeta, Yi Ma 외

Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort…

Object

Do You Need Proprioceptive States in Visuomotor Policies?

2025-09-23 · Juntu Zhao, Wenbo Lu, Di Zhang, Yufeng Liu 외 arxiv

Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together for precise control. However, in this stud…

Robot Manipulation

VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

2025-09-24 · Shaofeng Yin, Yanjie Ze, Hong-Xing Yu, C. Karen Liu 외 arxiv

Humanoid loco-manipulation in unstructured environments demands tight integration of egocentric perception and whole-body control. However, existing approaches either depend on external motion capture systems or fail to …

Hierarchical Graph Neural Networks for Proprioceptive 6D Pose Estimation of In-hand Objects

2023-06-28 · Alireza Rezazadeh, Snehal Dikhale, Soshi Iba, Nawid Jamali

Robotic manipulation, in particular in-hand object manipulation, often requires an accurate estimate of the object's 6D pose. To improve the accuracy of the estimated pose, state-of-the-art approaches in 6D object pose e…

6D Pose Estimation6D Pose Estimation using RGBGraph Neural NetworkObject+1