In agent control issues, the idea of combining reinforcement learning and planning has attracted much attention. Two methods focus on micro and macro action respectively. Their advantages would show together if there is a good cooperation between them. An essential for the cooperation is to find an appropriate boundary, assigning different functions to each method. Such boundary could be represented by parameters in a planning algorithm. In this paper, we create an optimization strategy for planning parameters, through analysis to the connection of reaction and planning; we also create a non-gradient method for accelerating the optimization. The whole algorithm can find a satisfactory setting of planning parameters, making full use of reaction capability of specific agents.
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games.
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
People's decisions about how to allocate their limited computational resources are essential to human intelligence. An important component of this metacognitive ability is deciding whether to continue thinking about what to do and move on to the next decision. Here, we show that people acquire this ability through learning and reverse-engineer the underlying learning mechanisms. Using a process-tracing paradigm that externalises human planning, we find that people quickly adapt how much planning they perform to the cost and benefit of planning. To discover the underlying metacognitive learning…
University of Stuttgart（斯图加特大学）；Stanford University（斯坦福大学）
Reinforcement learning-based path planning for multi-agent systems of varying size constitutes a research topic with increasing significance as progress in domains such as urban air mobility and autonomous aerial vehicles continues. Reinforcement learning with continuous state and action spaces is used to train a policy network that accommodates desirable path planning behaviors and can be used for time-critical applications. A Long Short-Term Memory module is proposed to encode an unspecified number of states for a varying, indefinite number of agents. The described training strategies and po…
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）
Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior knowledge of road network, which may be not available in certain situations. In this paper, we design a route planning algorithm based on deep reinforcement learning (DRL) for pedestrians. We use travel time consumption as the metric, and plan the route by predicting pedestrian flow in the road network. We put an agent, which is an intelligent robot, on a v…
Automatic Treatment Planning using Reinforcement Learning for High-dose-rate Prostate Brachytherapy
Department of Medical Physics, Memorial Sloan Kettering Cancer Center（医学物理系，纪念斯隆-凯特琳癌症中心）；Department of Radiation Oncology and Winship Cancer Institute, Emory University（放射肿瘤学系和Winship癌症研究所，埃默里大学）；Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University School of Medicine（Wallace H. Coulter生物医学工程系，佐治亚理工学院和埃默里大学医学院）；Department of Biomedical Informatics, Emory University（生物医学信息学系，埃默里大学）
A learning-driven automatic planning framework for proton PBS treatments of H&N cancers
Department of Radiation Medicine and Applied Sciences, University of California at San Diego（放射医学与应用科学系，加州大学圣地亚哥分校）；Amazon Inc.（亚马逊公司）；California Protons Cancer Therapy Center（加利福尼亚质子癌症治疗中心）
Arizona State University（亚利桑那州立大学）；Tufts University（塔夫茨大学）
The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them. There is also a lot of randomness from dice rolls, card-draws, and adversaries' strategies. This unpredictability is made worse when unknown novelties are added during gameplay. Given these challenges, Monopoly was one of the test beds chosen for the DARPA-SAILON program which aims to create agents that can detect and accommodate novelties. To handle the game complexities, we develop…
Residual Chain Prediction for Autonomous Driving Path Planning
Technical University of Munich（慕尼黑工业大学）；School of Computer Science, Nanjing University of Information Science & Technology（南京信息工程大学计算机学院）；School of Computer and Information Engineering, Fuyang Normal University（阜阳师范大学计算机与信息工程学院）
针对端到端自动驾驶路径规划中行为克隆因曼哈顿距离产生协变量偏移的问题，提出 Residual Chain Loss 动态调整损失以增强时序依赖，并在 nuScenes 上验证其性能提升。
Nonlinear dynamical social and political prediction algorithm for city planning and public participation using the Impulse Pattern Formulation
Institute of Systematic Musicology, University of Hamburg（汉堡大学系统音乐学研究所）；Hamburg University for Applied Sciences（汉堡应用科学大学）；Freie und Hansestadt Hamburg Landesbetrieb Immobilienmanagement und Grundvermögen（汉堡自由汉萨市不动产与土地管理局）
