paper-with-me

Papers

LOCO: Adaptive exploration in reinforcement learning via local estimation of contraction coefficients

2021-03-09 · ICLR Workshop SSL-RL 2021 5 · Manfred Diaz, Liam Paull, Pablo Samuel Castro

We offer a novel approach to balance exploration and exploitation in reinforcement learning (RL). To do so, we characterize an environment’s exploration difficulty via the Second Largest Eigenvalue Modulus (SLEM) of the Markov chain induced by uniform stochastic behaviour. Specifically, we investigate the connection of state-space coverage with the SLEM of this Markov chain and use the theory of contraction coefficients to derive estimates of this eigenvalue of interest. Furthermore, we introduce a method for estimating the contraction coefficients on a local level and leverage it to design a novel exploration algorithm. We evaluate our algorithm on a series of GridWorld tasks of varying sizes and complexity.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation

2026-02-16 · Morgan Byrd, Donghoon Baek, Kartik Garg, Hyunyoung Jung 외 arxiv

This paper presents Adaptive Whole-body Loco-Manipulation, AdaptManip, a fully autonomous framework for humanoid robots to perform integrated navigation, object lifting, and delivery. Unlike prior imitation learning-base…

Reinforcement Learning

FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion

2026-06-30 · Guanchen Lu, Yajuan Dun, Yi Zhou, Letian Tao 외 arxiv

Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy methods in robotic locomotion. However, the rapid increase of data v…

Reinforcement Learning

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning

2026-01-22 · Zichen Yan, Yuchen Hou, Shenao Wang, Yichao Gao 외 arxiv

Object-Goal Navigation (ObjectNav) requires an agent to autonomously explore an unknown environment and navigate toward target objects specified by a semantic label. While prior work has primarily studied zero-shot Objec…

Reinforcement Learning

GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains

2026-06-09 · Haoxuan Han, Chen Chen, Linao Gong, Xin Yang 외 arxiv

Humanoid robots have achieved strong locomotion capabilities, but reliable navigation on versatile terrains remains challenging because obstacle avoidance must be coordinated with dynamically feasible motion. In this wor…

Reinforcement Learning

VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion

2025-10-28 · Stanley Wu, Mohamad H. Danesh, Simon Li, Hanna Yurchyk 외 arxiv

Recent advancements in legged robot locomotion have facilitated traversal over increasingly complex terrains. Despite this progress, many existing approaches rely on end-to-end deep reinforcement learning (DRL), which po…

Reinforcement Learning