Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states

AUTOR(ES)

Silva, Valdinei Freire da, Costa, Anna Helena Reali

FONTE

Journal of the Brazilian Computer Society

DATA DE PUBLICAÇÃO

2009-09

RESUMO

Reinforcement Learning is carried out on-line, through trial-and-error interactions of the agent with the environment, which can be very time consuming when considering robots. In this paper we contribute a new learning algorithm, CFQ-Learning, which uses macro-states, a low-resolution discretisation of the state space, and a partial-policy to get around obstacles, both of them based on the complexity of the environment structure. The use of macro-states avoids convergence of algorithms, but can accelerate the learning process. In the other hand, partial-policies can guarantee that an agent fulfils its task, even through macro-state. Experiments show that the CFQ-Learning performs a good balance between policy quality and learning rate.

Documentos Relacionados

• An optical flow-based sensing system for reactive mobile robot navigation
• Autonomous robot s navigation based on monocular vision
• A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS
• Algoritmo Q-learning como estratégia de exploração e/ou explotação para metaheurísticas GRASP e algoritmo genético
• Building object-based maps for robot navigation.