English
Related papers

Related papers: Sub-policy Adaptation for Hierarchical Reinforceme…

200 papers

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

Machine Learning · Computer Science 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Advancing the dynamic loco-manipulation capabilities of quadruped robots in complex terrains is crucial for performing diverse tasks. Specifically, dynamic ball manipulation in rugged environments presents two key challenges. The first is…

Robotics · Computer Science 2025-04-22 Dongjie Zhu , Zhuo Yang , Tianhang Wu , Luzhou Ge , Xuesong Li , Qi Liu , Xiang Li

Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative…

Machine Learning · Computer Science 2026-04-02 Yu Xia , Canwen Xu , Zhewei Yao , Julian McAuley , Yuxiong He

Proximal Policy Optimization (PPO) is among the most widely used deep reinforcement learning algorithms, yet its theoretical foundations remain incomplete. Most importantly, convergence and understanding of fundamental PPO advantages remain…

Machine Learning · Computer Science 2026-02-04 Leif Doering , Daniel Schmidt , Moritz Melcher , Sebastian Kassing , Benedikt Wille , Tilman Aach , Simon Weissmann

We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is…

Machine Learning · Computer Science 2021-10-08 Sammy Christen , Lukas Jendele , Emre Aksan , Otmar Hilliges

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…

Machine Learning · Computer Science 2017-05-31 Joshua Achiam , David Held , Aviv Tamar , Pieter Abbeel

Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchical policy, where multiple option policies are in…

Machine Learning · Computer Science 2017-12-01 Takayuki Osa , Masashi Sugiyama

Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…

Machine Learning · Computer Science 2025-09-12 Somnath Hazra , Pallab Dasgupta , Soumyajit Dey

Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…

Machine Learning · Computer Science 2026-02-12 Linxuan Xia , Xiaolong Yang , Yongyuan Chen , Enyue Zhao , Deng Cai , Yasheng Wang , Boxi Wu

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…

Artificial Intelligence · Computer Science 2026-04-29 Simone Murari , Celeste Veronese , Daniele Meli

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional…

Machine Learning · Computer Science 2024-07-30 Tudor Cristea-Platon , Bogdan Mazoure , Josh Susskind , Walter Talbott

Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgoals. The main challenge of HRL is efficient discovery of the…

Machine Learning · Computer Science 2025-07-08 Sadegh Khorasani , Saber Salehkaleybar , Negar Kiyavash , Matthias Grossglauser

Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a…

Machine Learning · Computer Science 2025-09-08 Aditya Vikram Singh , Ethan Rathbun , Emma Graham , Lisa Oakley , Simona Boboila , Alina Oprea , Peter Chin

This paper presents a hierarchical reinforcement learning (RL) approach to address the agent grouping or pairing problem in cooperative multi-agent systems. The goal is to simultaneously learn the optimal grouping and agent policy. By…

Machine Learning · Computer Science 2025-01-14 Liyuan Hu

Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute…

Machine Learning · Computer Science 2024-05-09 Andrei Lixandru

Long-horizon manipulation tasks such as stacking represent a longstanding challenge in the field of robotic manipulation, particularly when using reinforcement learning (RL) methods which often struggle to learn the correct sequence of…

Robotics · Computer Science 2024-07-01 Jing Zhang , Emmanuel Dean , Karinne Ramirez-Amaro

Models with fewer parameters are necessary for the neural control of memory-limited, performant robots. Finding these smaller neural network architectures can be time-consuming. We propose HyperPPO, an on-policy reinforcement learning…

Robotics · Computer Science 2023-09-29 Shashank Hegde , Zhehui Huang , Gaurav S. Sukhatme

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu

Deep reinforcement learning (DRL) has emerged as a powerful framework for solving sequential decision-making problems, achieving remarkable success in a wide range of applications, including game AI, autonomous driving, biomedicine, and…

Machine Learning · Computer Science 2025-05-14 Yinghan Sun , Hongxi Wang , Hua Chen , Wei Zhang