中文
相关论文

相关论文: Feature Control as Intrinsic Motivation for Hierar…

200 篇论文

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

机器学习 · 计算机科学 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with…

人工智能 · 计算机科学 2026-02-24 Zhiqin Qian , Ryan Diaz , Sangwon Seo , Vaibhav Unhelkar

Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning…

人工智能 · 计算机科学 2025-09-17 Weiliang Zhang , Xiaohan Huang , Yi Du , Ziyue Qiao , Qingqing Long , Zhen Meng , Yuanchun Zhou , Meng Xiao

Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of…

机器学习 · 计算机科学 2021-05-25 Shariq Iqbal , Fei Sha

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…

机器学习 · 计算机科学 2021-02-11 Brendon Matusch , Jimmy Ba , Danijar Hafner

Traditional multi-agent reinforcement learning (MARL) algorithms, such as independent Q-learning, struggle when presented with partially observable scenarios, and where agents are required to develop delicate action sequences. This is often…

机器学习 · 计算机科学 2022-11-21 F. Bredell , H. A. Engelbrecht , J. C. Schoeman

We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities.…

机器学习 · 计算机科学 2026-02-04 Dan Haramati , Carl Qi , Tal Daniel , Amy Zhang , Aviv Tamar , George Konidaris

Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get…

机器学习 · 计算机科学 2020-01-13 Kai Jiang , XiaoLong Qin

Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling…

机器学习 · 计算机科学 2020-02-26 Benjamin Eysenbach , Xinyang Geng , Sergey Levine , Ruslan Salakhutdinov

In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversarial game, where an adversary searches over reward models, and…

机器学习 · 计算机科学 2025-04-23 Arnav Kumar Jain , Harley Wiltzer , Jesse Farebrother , Irina Rish , Glen Berseth , Sanjiban Choudhury

Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward problem in reinforcement learning (RL) by inferring dense reward functions from expert demonstrations. However, its performance in highly…

机器学习 · 计算机科学 2026-04-23 Bram Silue , Santiago Amaya-Corredor , Patrick Mannion , Lander Willem , Pieter Libin

In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems. Sparse reward is common in continuous control robotics tasks such as…

机器学习 · 计算机科学 2022-06-14 Souradip Chakraborty , Amrit Singh Bedi , Alec Koppel , Pratap Tokekar , Dinesh Manocha

This paper explores the combination of two intrinsic motivation strategies to improve the efficiency of reinforcement learning (RL) agents in environments with extreme sparse rewards, where traditional learning struggles due to infrequent…

机器学习 · 计算机科学 2025-08-27 André Quadros , Cassio Silva , Ronnie Alves

In this study, we address the problem of efficient exploration in reinforcement learning. Most common exploration approaches depend on random action selection, however these approaches do not work well in environments with sparse or no…

机器学习 · 计算机科学 2022-06-30 Doğay Kamar , Nazım Kemal Üre , Gözde Ünal

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…

机器学习 · 计算机科学 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able…

机器学习 · 计算机科学 2022-09-28 Desik Rengarajan , Sapana Chaudhary , Jaewon Kim , Dileep Kalathil , Srinivas Shakkottai

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

机器学习 · 计算机科学 2020-03-10 Neda Navidi

Decision-making in military aviation Prognostics and Health Management (PHM) faces significant challenges due to the "curse of dimensionality" in large-scale fleet operations, combined with sparse feedback and stochastic mission profiles.…

机器学习 · 计算机科学 2026-04-09 Yong Si , Mingfei Lu , Jing Li , Yang Hu , Guijiang Li , Yueheng Song , Zhaokui Wang

Designing suitable reward functions for numerous interacting intelligent agents is challenging in real-world applications. Inverse reinforcement learning (IRL) in mean field games (MFGs) offers a practical framework to infer reward…

机器学习 · 计算机科学 2025-09-05 Yang Chen , Xiao Lin , Bo Yan , Libo Zhang , Jiamou Liu , Neset Özkan Tan , Michael Witbrock

Deep Reinforcement Learning (DRL) has achieved great success in solving complicated decision-making problems. Despite the successes, DRL is frequently criticized for many reasons, e.g., data inefficient, inflexible and intractable reward…

机器学习 · 计算机科学 2023-02-07 Weiqin Chen