中文
相关论文

相关论文: No Prior Mask: Eliminate Redundant Action for Deep…

200 篇论文

Intelligent decision-making within large and redundant action spaces remains challenging in deep reinforcement learning. Considering similar but ineffective actions at each step can lead to repetitive and unproductive trials. Existing…

机器学习 · 计算机科学 2025-01-27 Wenzhang Liu , Lianjun Jin , Lu Ren , Chaoxu Mu , Changyin Sun

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

Deep reinforcement learning (RL) has gained widespread adoption in recent years but faces significant challenges, particularly in unknown and complex environments. Among these, high-dimensional action selection stands out as a critical…

机器学习 · 统计学 2025-07-08 Wenbo Zhang , Hengrui Cai

In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide…

机器人学 · 计算机科学 2021-04-20 Ondrej Biza , Dian Wang , Robert Platt , Jan-Willem van de Meent , Lawson L. S. Wong

In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action…

机器学习 · 计算机科学 2022-06-01 Shengyi Huang , Santiago Ontañón

Continuous action spaces in reinforcement learning (RL) are commonly defined as multidimensional intervals. While intervals usually reflect the action boundaries for tasks well, they can be challenging for learning because the typically…

机器学习 · 计算机科学 2024-11-06 Roland Stolz , Hanna Krasowski , Jakob Thumm , Michael Eichelbeck , Philipp Gassert , Matthias Althoff

Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to…

机器学习 · 计算机科学 2019-02-26 Tom Zahavy , Matan Haroush , Nadav Merlis , Daniel J. Mankowitz , Shie Mannor

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

机器学习 · 计算机科学 2019-09-18 Zac Wellmer , James Kwok

Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in…

机器学习 · 计算机科学 2023-05-15 Leo Ardon , Alberto Pozanco , Daniel Borrajo , Sumitra Ganesh

One of the key approaches to save samples in reinforcement learning (RL) is to use knowledge from an approximate model such as its simulator. However, how much does an approximate model help to learn a near-optimal policy of the true…

机器学习 · 计算机科学 2020-07-15 Fei Feng , Wotao Yin , Lin F. Yang

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

机器学习 · 计算机科学 2017-01-11 Tanmay Shankar , Santosha K. Dwivedy , Prithwijit Guha

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…

机器学习 · 计算机科学 2023-04-04 Jiaqi Ye , Xiaodong Li , Pangjing Wu , Feng Wang

Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor…

机器人学 · 计算机科学 2017-03-03 Ali Ghadirzadeh , Atsuto Maki , Danica Kragic , Mårten Björkman

Deep learning classifiers face significant challenges when dealing with heterogeneous multi-modal and multi-organ biomedical datasets. The low-level feature distinguishability limited to imaging-modality hinders the classifiers' ability to…

图像与视频处理 · 电气工程与系统科学 2025-02-04 Mehmet Can Yavuz , Yang Yang

We introduce PPOPT - Proximal Policy Optimization using Pretraining, a novel, model-free deep-reinforcement-learning algorithm that leverages pretraining to achieve high training efficiency and stability on very small training samples in…

机器学习 · 计算机科学 2025-11-25 Ruoxing Yang

This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…

机器学习 · 计算机科学 2025-04-28 Simon Hakenes , Tobias Glasmachers

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as "zero-shot learning", this ability remains…

机器学习 · 计算机科学 2025-03-12 Siddhant Agarwal , Harshit Sikchi , Peter Stone , Amy Zhang

Reinforcement learning often needs to deal with the exponential growth of states and actions when exploring optimal control in high-dimensional spaces (often known as the curse of dimensionality). In this work, we address this issue by…

机器学习 · 计算机科学 2023-06-23 Yining Li , Peizhong Ju , Ness Shroff

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby,…

机器人学 · 计算机科学 2021-01-26 Michael Everett , Yu Fan Chen , Jonathan P. How

Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity,…

密码学与安全 · 计算机科学 2024-05-14 Zhixiong Zhuang , Maria-Irina Nicolae , Mario Fritz
‹ 上一页 1 2 3 10 下一页 ›