paper-with-me

홈 › Papers

Action Pick-up in Dynamic Action Space Reinforcement Learning

2023-04-03 · Jiaqi Ye, XiaoDong Li, Pangjing Wu, Feng Wang

Most reinforcement learning algorithms are based on a key assumption that Markov decision processes (MDPs) are stationary. However, non-stationary MDPs with dynamic action space are omnipresent in real-world scenarios. Yet problems of dynamic action space reinforcement learning have been studied by many previous works, how to choose valuable actions from new and unseen actions to improve learning efficiency remains unaddressed. To tackle this problem, we propose an intelligent Action Pick-up (AP) algorithm to autonomously choose valuable actions that are most likely to boost performance from a set of new actions. In this paper, we first theoretically analyze and find that a prior optimal policy plays an important role in action pick-up by providing useful knowledge and experience. Then, we design two different AP methods: frequency-based global method and state clustering-based local method, based on the prior optimal policy. Finally, we evaluate the AP on two simulated but challenging environments where action spaces vary over time. Experimental results demonstrate that our proposed AP has advantages over baselines in learning efficiency.

📄 PDF Abstract BibTeX arXiv:2304.00873

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Learning to Manipulate Deformable Objects without Demonstrations

2019-10-29 · Yilin Wu, Wilson Yan, Thanard Kurutach, Lerrel Pinto 외

In this paper we tackle the problem of deformable object manipulation through model-free visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we propose two key ideas that accelerate …

Deformable Object ManipulationObjectReinforcement LearningReinforcement Learning (RL)

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

2026-06-17 · Seyed Alireza Azimi, Homayoon Farrahi, Abhishek Naik, Colin Bellinger 외 arxiv

In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, join…

Reinforcement Learning

SynPick: A Dataset for Dynamic Bin Picking Scene Understanding

2021-07-10 · Arul Selvam Periyasamy, Max Schwarz, Sven Behnke

We present SynPick, a synthetic dataset for dynamic scene understanding in bin-picking scenarios. In contrast to existing datasets, our dataset is both situated in a realistic industrial application domain -- inspired by…

ARCDataset GenerationPose EstimationScene Understanding

PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planning

2023-03-02 · Halid Abdulrahim Kadi, Kasim Terzic

Why do Recurrent State Space Models such as PlaNet fail at cloth manipulation tasks? Recent work has attributed this to the blurry prediction of the observation, which makes it difficult to plan directly in the latent sp…

State Space Models

Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems

2025-11-21 · Zengyu Zou, Jingyuan Wang, Yixuan Huang, Junjie Wu arxiv

This paper addresses the cooperative Multi-Vehicle Dynamic Pickup and Delivery Problem with Stochastic Requests (MVDPDPSR) and proposes an end-to-end centralized decision-making framework based on sequence-to-sequence, n…

Reinforcement Learning