info:eu-repo/semantics/other
GAME BASED DEEP REINFORCEMENT LEARNING FOR TARGET TRACKING
Autor
Marco Antonio Esquivel Basaldua
Institución
Resumen
This work proposes a methodology for solving the tracking problem under classic visibility in the 2D Euclidean space for a pair of omnidirectional antagonistic players, a pursuer and an evader.
The methodology starts proposing motion policies for the players in a discrete state-space applying optimal motion planning in a pursuit-evasion game. The first approach in the
continuous state-space consists of two neural networks, one per each player, acting as motion policies whose entries are states in the environment and outputs are the actions to perform.
The policies are trained from the behaviour in the discrete state-space. Finally, we implement an improvement for the pursuer motion policy using deep reinforcement learning (DRL) considering
a fixed trajectory for the evader. In all these cases, the action-space is discrete. A DRL approach from scratch is compared to a initialized DRL approach, using the weights in the neural network
trained from the optimal motion planning, and a DRL approach using a master policy (the same neural network trained from the optimal motion planning) which generates transitions in training for
a pursuer in two proposed environments. Results show that a simple initialization is enough to achieve favorable outcomes in a simple environment while the use of a master policy is preferred in a more complex one.
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Compendio de innovaciones socioambientales en la frontera sur de México
Adriana Quiroga -
Caminar el cafetal: perspectivas socioambientales del café y su gente
Eduardo Bello Baltazar; Lorena Soto_Pinto; Graciela Huerta_Palacios; Jaime Gomez -
Cambio social y agrícola en territorios campesinos. Respuestas locales al régimen neoliberal en la frontera sur de México
Luis Enrique García Barrios; Eduardo Bello Baltazar; Manuel Roberto Parra Vázquez