Market-Based Dynamic Task Allocation Using Heuristically Accelerated Reinforcement Learning

Gurzoni, José Angelo; Tonidandel, Flavio; Bianchi, Reinaldo A. C.

doi:10.1007/978-3-642-24769-9_27

Cited by 7 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comprehensive analysis of a general batch RL framework for learning challenging and complex behaviors in robot soccer is reported in [15]. Despite convergence guarantees, Q(λ) [21] with linear function approximation has been used in role assignment in robot soccer [5] and faster learning is observed with the introduction of heuristically accelerated methods [3]. The dynamic role allocation framework based on dynamic programming is described in [6] for real-time soccer environments.…”

Section: Related Workmentioning

confidence: 99%

Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation

Abeyruwan¹,

Seekircher²,

Visser³

2014

Preprint

View full text Add to dashboard Cite

Collecting and maintaining accurate world knowledge in a dynamic, complex, adversarial, and stochastic environment such as the RoboCup 3D Soccer Simulation is a challenging task. Knowledge should be learned in real-time with time constraints. We use recently introduced Off-Policy Gradient Descent algorithms within Reinforcement Learning that illustrate learnable knowledge representations for dynamic role assignments. The results show that the agents have learned competitive policies against the top teams from the RoboCup 2012 competitions for three vs three, five vs five, and seven vs seven agents. We have explicitly used subsets of agents to identify the dynamics and the semantics for which the agents learn to maximize their performance measures, and to gather knowledge about different objectives, so that all agents participate effectively and efficiently within the group.

show abstract

Section: Related Workmentioning

confidence: 99%

Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation

Abeyruwan¹,

Seekircher²,

Visser³

2014

Preprint

View full text Add to dashboard Cite

show abstract

“…It extends the Q-Learning algorithm by using the heuristic function to influence the action choice. HAQL has been used in a variety of domains such as autonomous mobile robot navigation (Bianchi et al, 2008), RoboCup 2D Simulation (Celiberto et al, 2007), Multi-Robot Task Allocation (MRTA) applied in the RoboCup Small Size League (Gurzoni et al, 2011); it was also extended to deal with multiagent problems . The HAQL algorithm is shown in Algorithm 1.…”

Section: Introductionmentioning

confidence: 99%

Transferring knowledge as heuristics in reinforcement learning: A case-based approach

Bianchi

Celiberto

Santos

et al. 2015

Artificial Intelligence

View full text Add to dashboard Cite

The goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure in one domain (the target) that are obtained from another (simpler) domain (the source domain). This meta-algorithm works in three stages: first, it uses a Reinforcement Learning step to learn a task on the source domain, storing the knowledge thus obtained in a case base; second, it does an unsupervised mapping of the source-domain actions to the target-domain actions; and, third, the case base obtained in the first stage is used as heuristics to speed up the learning process in the target domain.A set of empirical evaluations were conducted in two target domains: the 3D mountain car (using a learned case base from a 2D simulation) and stability learning for a humanoid robot in the Robocup 3D Soccer Simulator (that uses knowledge learned from the Acrobot domain). The results attest that our transfer learning algorithm outperforms recent heuristically-accelerated reinforcement learning and transfer learning algorithms.

show abstract

Heuristically-Accelerated Reinforcement Learning: A Comparative Analysis of Performance

Martins

Bianchi

2014

Towards Autonomous Robotic Systems

View full text Add to dashboard Cite

Market-Based Dynamic Task Allocation Using Heuristically Accelerated Reinforcement Learning

Cited by 7 publications

References 14 publications

Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation

Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation

Transferring knowledge as heuristics in reinforcement learning: A case-based approach

Heuristically-Accelerated Reinforcement Learning: A Comparative Analysis of Performance

Contact Info

Product

Resources

About