中文
相关论文

相关论文: Mixing Human Demonstrations with Self-Exploration …

200 篇论文

Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often…

机器学习 · 计算机科学 2022-02-18 Yizhi Yuan , Marcelo G Mattar

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

机器学习 · 计算机科学 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular…

系统与控制 · 电气工程与系统科学 2024-10-08 Jiyi Wang , Likai Tang , Huimiao Chen , Marcelo G Mattar , Sen Song

Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the…

机器人学 · 计算机科学 2020-11-12 Pierre Aumjaud , David McAuliffe , Francisco Javier Rodríguez Lera , Philip Cardiff

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…

机器学习 · 计算机科学 2022-10-06 Fengdi Che , Xiru Zhu , Doina Precup , David Meger , Gregory Dudek

Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and…

人工智能 · 计算机科学 2022-07-26 Sam Blakeman , Denis Mareschal

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that…

机器学习 · 计算机科学 2019-04-09 Gabriel V. de la Cruz , Yunshu Du , Matthew E. Taylor

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…

机器人学 · 计算机科学 2022-05-31 Haochen Liu , Zhiyu Huang , Jingda Wu , Chen Lv

In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games. However, the current manifestation of DRL is…

机器学习 · 计算机科学 2019-07-30 Ngoc Duy Nguyen , Saeid Nahavandi , Thanh Nguyen

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…

机器学习 · 计算机科学 2025-12-05 Yasuhiro Fujita

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

机器学习 · 计算机科学 2025-04-29 Muhammad Qasim Elahi , Somtochukwu Oguchienti , Maheed H. Ahmed , Mahsa Ghasemi

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

机器学习 · 计算机科学 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

We study the problem of sample efficient reinforcement learning, where prior data such as demonstrations are provided for initialization in lieu of a dense reward signal. A natural approach is to incorporate an imitation learning objective,…

机器学习 · 计算机科学 2025-06-10 Perry Dong , Alec M. Lessing , Annie S. Chen , Chelsea Finn

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning…

人工智能 · 计算机科学 2018-10-18 Vlad Firoiu , Tina Ju , Josh Tenenbaum

Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human students, we know that the demonstrations must fall within a…

机器学习 · 计算机科学 2019-10-29 Daniel Seita , David Chan , Roshan Rao , Chen Tang , Mandi Zhao , John Canny

Deep reinforcement learning (DRL) is a promising way to achieve human-like autonomous driving. However, the low sample efficiency and difficulty of designing reward functions for DRL would hinder its applications in practice. In light of…

机器人学 · 计算机科学 2021-10-29 Zhiyu Huang , Jingda Wu , Chen Lv

Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem…

人工智能 · 计算机科学 2022-12-15 Hugo Muñoz , Ernesto Portugal , Angel Ayala , Bruno Fernandes , Francisco Cruz

How does a user's prior experience with deep learning impact accuracy? We present an initial study based on 31 participants with different levels of experience. Their task is to perform hyperparameter optimization for a given deep learning…

计算机视觉与模式识别 · 计算机科学 2020-08-14 Kanav Anand , Ziqi Wang , Marco Loog , Jan van Gemert

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce…

机器人学 · 计算机科学 2017-07-11 Josh Merel , Yuval Tassa , Dhruva TB , Sriram Srinivasan , Jay Lemmon , Ziyu Wang , Greg Wayne , Nicolas Heess

Cooperative multi-agent reinforcement learning (MARL) is a challenging task, as agents must learn complex and diverse individual strategies from a shared team reward. However, existing methods struggle to distinguish and exploit important…

多智能体系统 · 计算机科学 2023-05-26 Xunhan Hu , Jian Zhao , Wengang Zhou , Ruili Feng , Houqiang Li