English
Related papers

Related papers: CIM: Constrained Intrinsic Motivation for Sparse-R…

200 papers

Driving behavior modeling is of great importance for designing safe, smart, and personalized autonomous driving systems. In this paper, an internal reward function-based driving model that emulates the human's decision-making mechanism is…

Robotics · Computer Science 2021-07-21 Zhiyu Huang , Jingda Wu , Chen Lv

Reward machines are an established tool for dealing with reinforcement learning problems in which rewards are sparse and depend on complex sequences of actions. However, existing algorithms for learning reward machines assume an overly…

Machine Learning · Computer Science 2025-10-20 Jan Corazza , Ivan Gavran , Daniel Neider

Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…

Machine Learning · Computer Science 2025-09-29 Micha Livne

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoning. While dense…

This paper explores an intrinsic motivation for mutual awareness, hypothesizing that humans possess a fundamental drive to understand and to be understood even in the absence of extrinsic rewards. Through simulations of the perceptual…

Machine Learning · Computer Science 2025-04-11 Chrisantha Fernando , Dylan Banarse , Simon Osindero

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current multi-agent…

Multiagent Systems · Computer Science 2022-11-11 Zixian Ma , Rose Wang , Li Fei-Fei , Michael Bernstein , Ranjay Krishna

Extrinsic calibration is essential for multi-sensor fusion, existing methods rely on structured targets or fully-excited data, limiting real-world applicability. Online calibration further suffers from weak excitation, leading to unreliable…

Robotics · Computer Science 2025-08-11 Baorun Li , Chengrui Zhu , Siyi Du , Bingran Chen , Jie Ren , Wenfei Wang , Yong Liu , Jiajun Lv

For identifying the non-Gaussian impulsive noise systems, normalized LMP (NLMP) has been proposed to combat impulsive-inducing instability. However, the standard algorithm is without considering the inherent sparse structure distribution of…

Information Theory · Computer Science 2015-03-04 Wentao Ma , Hua Qu , Jihong Zhao , Badong Chen , Guan Gui

As a quantum-inspired, non-traditional analog solver architecture, the analog Ising machine (AIM) has emerged as a distinctive computational paradigm to address the rapidly growing demand for computational power. However, the mathematical…

Quantum Physics · Physics 2026-02-06 Langyu Li , Ruoyu Wu , Yong Wang , Guofeng Zhang , Jinhu Lü , Qing Gao , Yu Pan

This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward problems, the reward is rare, which means that the agent will…

Machine Learning · Computer Science 2022-05-03 Pawel Ladosz , Lilian Weng , Minwoo Kim , Hyondong Oh

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

Artificial Intelligence · Computer Science 2025-12-05 Shuyuan Zhang

This study develops a framework for a class of constant modulus (CM) optimization problems, which covers binary constraints, discrete phase constraints, semi-orthogonal matrix constraints, non-negative semi-orthogonal matrix constraints,…

Signal Processing · Electrical Eng. & Systems 2024-11-12 Junbin Liu , Ya Liu , Wing-Kin Ma , Mingjie Shao , Anthony Man-Cho So

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and…

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

Incorporating safety is an essential prerequisite for broadening the practical applications of reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov Decision Processes (CMDPs) are leveraged, which…

Machine Learning · Computer Science 2023-11-03 Jaafar Mhamed , Shangding Gu

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and labeled datasets, which eliminates the time-consuming data collection in online RL. However, offline RL still bears a large burden of…

Machine Learning · Computer Science 2023-10-17 Jinxin Liu , Lipeng Zu , Li He , Donglin Wang

Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode…

Machine Learning · Computer Science 2026-05-21 Jiwoo Hong , Shao Tang , Zhipeng Wang

Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce…

Machine Learning · Computer Science 2025-08-29 Shengfan Cao , Eunhyek Joa , Francesco Borrelli

We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty of the surprise rather than the surprise norm. We estimate…

Machine Learning · Computer Science 2024-02-01 Hung Le , Kien Do , Dung Nguyen , Svetha Venkatesh

Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks,…

Robotics · Computer Science 2024-07-10 Gautham Vasan , Yan Wang , Fahim Shahriar , James Bergstra , Martin Jagersand , A. Rupam Mahmood
‹ Prev 1 8 9 10 Next ›