Skip to Main content Skip to Navigation
Conference papers

Real Time Robot Policy Adaptation Based on Intelligent Algorithms

Abstract : In this paper we present a new method for robot real time policy adaptation by combining learning and evolution. The robot adapts the policy as the environment conditions change. In our method, we apply evolutionary computation to find the optimal relation between reinforcement learning parameters and robot performance. The proposed algorithm is evaluated in the simulated environment of the Cyber Rodent (CR) robot, where the robot has to increase its energy level by capturing the active battery packs. The CR robot lives in two environments with different settings that replace each other four times. Results show that evolution can generate an optimal relation between the robot performance and exploration-exploitation of reinforcement learning, enabling the robot to adapt online its strategy as the environment conditions change.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-01571490
Contributor : Hal Ifip <>
Submitted on : Wednesday, August 2, 2017 - 4:22:30 PM
Last modification on : Thursday, March 5, 2020 - 5:42:24 PM

File

978-3-642-23960-1_1_Chapter.pd...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Genci Capi, Hideki Toda, Shin-Ichiro Kaneko. Real Time Robot Policy Adaptation Based on Intelligent Algorithms. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.1-10, ⟨10.1007/978-3-642-23960-1_1⟩. ⟨hal-01571490⟩

Share

Metrics

Record views

79

Files downloads

103