A Reinforcement Learning Technique with an Adaptive Action Generator for a Multi-robot System

We have developed a new reinforcement learning (RL) technique called Bayesian-discrimination-function-based reinforcement learning (BRL). BRL is unique, in that it does not have state and action spaces designed by a human designer, but adaptively segments them through the learning process. Compared to other standard RL algorithms, BRL has been proven to be more effective in handling problems encountered by multi-robot systems (MRS), which operate in a learning environment that is naturally dynamic. Furthermore, we have developed an extended form of BRL in order to improve the learning efficiency. Instead of generating a random action when a robot functioning within the framework of the standard BRL encounters an unknown situation, the extended BRL generates an action determined by linear interpolation among the rules that have high similarity to the current sensory input. In this study, we investigate the robustness of the extended BRL through further experiments. In both physical experiments and computer simulations, the extended BRL shows higher robustness and relearning ability against an environmental change as compared to the standard BRL.

• Publication year

  2008

• Venue

  Simulation of Adaptive Behavior

• Publication date

  2008-07-07

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1007/978-3-540-69134-1_25
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Advances in Neural Information Processing Systems pp MIT Press Generalization in Reinforcement Learning Successful Examples Using Sparse Coarse Coding

  2010cited by this paper
• A machine-learning approach to multi-robot coordination

  2008cited by this paper
• Improving Search Efficiency in the Action Space of an Instance-Based Reinforcement Learning Technique for Multi-robot Systems

  2007cited by this paper
• Autonomous Role Assignment in a Homogeneous Multi-Robot System

  2005cited by this paper
• Distributed Control of Multi-Robot Systems Engaged in Tightly Coupled Tasks

  2004cited by this paper
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

  2004cited by this paper
• Natural Actor-Critic

  2003cited by this paper
• Evolution of Collective Behavior in a Team of Physically Linked Robots

  2003cited by this paper
• Advances in Artificial Life

  2003cited by this paper
• Sold!: auction methods for multirobot coordination

  2002cited by this paper
• Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning

  2000cited by this paper
• Reinforcement Learning in Continuous Time and Space

  2000cited by this paper
• Initial experiments on reinforcement learning control of cooperative manipulations

  2000cited by this paper
• ALLIANCE: an architecture for fault tolerant multirobot cooperation

  1998cited by this paper
• Load sharing of decentralized-controlled multiple mobile robots handling a single object

  1997cited by this paper
• Evolutionary robotics: the Sussex approach

  1997cited by this paper
• The use of perceptual cues in multi-robot box-pushing

  1996cited by this paper
• Action-based sensor space categorization for robot learning

  1996cited by this paper
• Reasonable performance in less learning time by real robot based on incremental state space segmentation

  1996cited by this paper
• Cooperative multi-robot box-pushing

  1995cited by this paper
• Learning to Coordinate without Sharing Information

  1994cited by this paper
• Scaling Up Reinforcement Learning for Robot Control

  1993cited by this paper
• Pattern classification and scene analysis

  1974cited by this paper

• Training an Under-actuated Gripper for Grasping Shallow Objects Using Reinforcement Learning

  2020cites this paper
• Modeling Swarm Systems and Formal Design Methods

  2018cites this paper
• Multi-Scale Spatial Cognition Models and Bio-Inspired Robot Navigation

  2017cites this paper
• Representation and generalization in autonomous reinforcement learning

  2017cites this paper
• Distributed Multi-Robot Learning using Particle Swarm Optimization

  2015cites this paper
• Reinforcement learning in robotics: A survey

  2013cites this paper
• A comparison of PSO and Reinforcement Learning for multi-robot obstacle avoidance

  2013cites this paper
• Learning Motor Skills - From Algorithms to Robot Experiments

  2013cites this paper
• Instance-Based Reinforcement Learning Technique with a Meta-learning Mechanism for Robust Multi-Robot Systems

  2011cites this paper