中文
相关论文

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

200 篇论文

TAMER has proven to be a powerful interactive reinforcement learning method for allowing ordinary people to teach and personalize autonomous agents' behavior by providing evaluative feedback. However, a TAMER agent planning with UCT---a…

人工智能 · 计算机科学 2019-04-19 Guangliang Li , Randy Gomez , Keisuke Nakamura , Jinying Lin , Qilei Zhang , Bo He

Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the…

机器学习 · 计算机科学 2022-08-02 Paweł Wawrzyński , Wojciech Masarczyk , Mateusz Ostaszewski

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

机器学习 · 计算机科学 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor

While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an…

机器学习 · 计算机科学 2021-05-21 Max Schwarzer , Ankesh Anand , Rishab Goel , R Devon Hjelm , Aaron Courville , Philip Bachman

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

机器学习 · 计算机科学 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…

机器学习 · 计算机科学 2025-05-20 Kaiyan Zhao , Yiming Wang , Yuyang Chen , Yan Li , Leong Hou U , Xiaoguang Niu

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual…

Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…

机器学习 · 计算机科学 2022-06-15 Thibault Lahire , Matthieu Geist , Emmanuel Rachelson

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

人工智能 · 计算机科学 2018-10-30 Zhang-Wei Hong , Tzu-Yun Shann , Shih-Yang Su , Yi-Hsiang Chang , Chun-Yi Lee

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

机器学习 · 计算机科学 2023-04-12 Qingfeng Lan , Yangchen Pan , Jun Luo , A. Rupam Mahmood

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

机器学习 · 计算机科学 2021-02-04 Mirza Ramicic , Andrea Bonarini

In the era of deep reinforcement learning, making progress is more complex, as the collected experience must be compressed into a deep model for future exploitation and sampling. Many papers have shown that training a deep learning policy…

机器学习 · 计算机科学 2025-08-05 Glen Berseth

This paper presents CONTHER, a novel reinforcement learning algorithm designed to efficiently and rapidly train robotic agents for goal-oriented manipulation tasks and obstacle avoidance. The algorithm uses a modified replay buffer inspired…

机器人学 · 计算机科学 2025-03-21 Maria Makarova , Qian Liu , Dzmitry Tsetserukou

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images…

机器学习 · 计算机科学 2019-07-31 Gabriel V. de la Cruz , Yunshu Du , Matthew E. Taylor

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help…

机器学习 · 计算机科学 2020-08-19 Arash Tavakoli , Vitaly Levdik , Riashat Islam , Christopher M. Smith , Petar Kormushev

Online recommendation requires handling rapidly changing user preferences. Deep reinforcement learning (DRL) is gaining interest as an effective means of capturing users' dynamic interest during interactions with recommender systems.…

信息检索 · 计算机科学 2021-10-22 Xiaocong Chen , Lina Yao , Xianzhi Wang , Julian McAuley

Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement…

人工智能 · 计算机科学 2017-11-07 Richard Liaw , Sanjay Krishnan , Animesh Garg , Daniel Crankshaw , Joseph E. Gonzalez , Ken Goldberg

Reinforcement learning algorithms can acquire policies for complex tasks autonomously. However, the number of samples required to learn a diverse set of skills can be prohibitively large. While meta-reinforcement learning methods have…

机器学习 · 计算机科学 2020-06-17 Russell Mendonca , Xinyang Geng , Chelsea Finn , Sergey Levine

This paper deals with robotic lever control using Explainable Deep Reinforcement Learning. First, we train a policy by using the Deep Deterministic Policy Gradient algorithm and the Hindsight Experience Replay technique, where the goal is…

机器人学 · 计算机科学 2021-10-08 Sindre Benjamin Remman , Anastasios M. Lekkas

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

机器学习 · 计算机科学 2024-05-09 Wanqi Xue , Bo An , Shuicheng Yan , Zhongwen Xu