.png){kind=icon}
返回
Batch Prioritization in Multigoal Reinforcement Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.3012204.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In multigoal reinforcement learning, an agent interacts with an environment and learns to achieve multiple goals. The goal-conditioned policy is trained to effectively generalize its behavior for multiple goals. During training, the experiences collected by the agent are randomly sampled from a replay buffer. Because biased sampling of achieved goals affects the success rate of a given task, it should be avoided by considering the valid goal space, introduced here as the set of goals to achieve, and the current competence of the policy. To this end, a novel prioritization method for creation of batches, e.g., collections of samples, is proposed. Candidate batches are sampled and associated with costs; in each iteration the batch with the minimum cost is chosen to train the policy. The cost function is modeled by an intended goal, which is proposed as a hypothetical goal that the policy is trying to learn in each cycle, and the information of the valid goal space. The minimum cost of the batch selected for each iteration decreases throughout training as the policy learns to achieve goals near the center of the valid goal space. The proposed batch prioritization method is combined with hindsight experience replay (HER) for experiments in robotic control tasks presented in the OpenAI gym suite to demonstrate learning performance comparable to that of other state-of-the-art prioritization methods. As a result, the proposed batch prioritization method can achieve improved learning performance in 4 out of 5 tasks, particularly for harder tasks. The experimental results suggest that the proposed method for the creation of training batches, using the valid goal space information and current competence of the policy, can enhance learning performance in multigoal tasks with high-dimensional goal space.
Keyword:
Training
Task analysis
Learning (artificial intelligence)
Robots
Erbium
Cost function
Aerospace electronics
Experience replay
batch prioritization
goal distribution
reinforcement learning
intended goal
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Guided goal generation for hindsight multi-goal reinforcement learning事后多目标强化学习的引导式目标生成.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Topology Control and Routing Based on Adaptive RF/FSO Switching in Space-Air Integrated Networks
PREAI
分享收藏Rewards Prediction-Based Credit Assignment for Reinforcement Learning With Sparse Binary Rewards基于奖励预测的信用分配，用于具有稀疏二进制奖励的强化学习IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏ICT for informal workers in Sub-Saharan Africa: Systematic review and analysis撒哈拉以南非洲非正规工人的信通技术: 系统回顾和分析
PREAI
分享收藏
查看更多内容