Loading...
Search for:
skill-acquisition
0.005 seconds
A novel graphical approach to automatic abstraction in reinforcement learning
, Article Robotics and Autonomous Systems ; Volume 61, Issue 8 , 2013 , Pages 821-835 ; 09218890 (ISSN) ; Beigy, H ; Sharif University of Technology
2013
Abstract
Recent researches on automatic skill acquisition in reinforcement learning have focused on subgoal discovery methods. Among them, algorithms based on graph partitioning have achieved higher performance. In this paper, we propose a new automatic skill acquisition framework based on graph partitioning approach. The main steps of this framework are identifying subgoals and discovering useful skills. We propose two subgoal discovery algorithms, which use spectral analysis on the transition graph of the learning agent. The first proposed algorithm, incorporates k′-means algorithm with spectral clustering. In the second algorithm, eigenvector centrality measure is utilized and options are...
A graph-theoretic approach toward autonomous skill acquisition in reinforcement learning
, Article Evolving Systems ; Volume 9, Issue 3 , 2018 , Pages 227-244 ; 18686478 (ISSN) ; Taghizadeh, N ; Beigy, H ; Sharif University of Technology
Springer Verlag
2018
Abstract
Hierarchical reinforcement learning facilitates learning in large and complex domains by exploiting subtasks and creating hierarchical structures using these subtasks. Subtasks are usually defined through finding subgoals of the problem. Providing mechanisms for autonomous subgoal discovery and skill acquisition is a challenging issue in reinforcement learning. Among the proposed algorithms, a few of them are successful both in performance and also efficiency in terms of the running time of the algorithm. In this paper, we study four methods for subgoal discovery which are based on graph partitioning. The idea behind the methods proposed in this paper is that if we partition the transition...
Exact and Metaheuristic Solution for Multi-skilled Project Scheduling Problem with Regards to Set-up Time
, M.Sc. Thesis Sharif University of Technology ; Shadrokh, Shahram (Supervisor)
Abstract
Multi-mode resource-constrained project scheduling problem (MRCPSP) is considered one of the most complex and most frequently applied problems in the science field of project scheduling and the science of operations research, which recently a new version of it called multi-skilled project scheduling problem (MSPSP) has emerged in research studies. The purpose of this new problem is to schedule activities with respect to precedence relationships and resource constraints of the workforce types with multiple skills, such that the requirements of any activity for a subset of skills must be met by the qualified members of the project. In this study, in addition to observing the constraints and...
Autonomous Skill Acquisition in Reinforcement Learning Based on Graph Clustering
, M.Sc. Thesis Sharif University of Technology ; Beigy, Hamid (Supervisor)
Abstract
Reinforcement Learning (RL) is a branch of machine learning that tries to improve agent’s behaviour through interaction with environment and receiving reinforcement signal. As the size of environment increases, decision-making would be more difficult and learning time will increase. On of the main approaches for decreasing learning complexity is to define skills. Skill is a behavioural unit consists of primitive actions. Humans learn and use a lot of skills in their life. Walking, eating, passing the door to reach kitchen and going to airport for travelling are examples of such skills that humans utilize them for daily activities. Agent can learn skills once and then uses them in other...
Automatic Skill Learning Using Community Detection Approach
, M.Sc. Thesis Sharif University of Technology ; Beigy, Hamid (Supervisor)
Abstract
Reinforcement learning is a learning method that uses reward and penalty feedbacks, having no information about the right action. In this method, agent gets the state of environment and selects an action among its permissible set of actions, regarding its policy and the given state. Environment, expresses an evaluation, in form of a reinforcement signal and a change in state, as a response for agent’s action. Afterward, the agent updates its policy considering received signal in order to maximize its long term reward. Reinforcement learning rapidly converges to the optimal solution, only if there are few states and actions, but there are lots of domains that consist of too many states and...
Using strongly connected components as a basis for autonomous skill acquisition in reinforcement learning
, Article 6th International Symposium on Neural Networks, ISNN 2009, Wuhan, 26 May 2009 through 29 May 2009 ; Volume 5551 LNCS, Issue PART 1 , 2009 , Pages 794-803 ; 03029743 (ISSN); 3642015069 (ISBN); 9783642015069 (ISBN) ; Beigy, H ; Sharif University of Technology
2009
Abstract
Hierarchical reinforcement learning (HRL) has had a vast range of applications in recent years. Preparing mechanisms for autonomous acquisition of skills has been a main topic of research in this area. While different methods have been proposed to achieve this goal, few methods have been shown to be successful both in performance and also efficiency in terms of time complexity of the algorithm. In this paper, a linear time algorithm is proposed to find subgoal states of the environment in early episodes of learning. Having subgoals available in early phases of a learning task, results in building skills that dramatically increase the convergence rate of the learning process. © 2009 Springer...