[图书][B] Integration of partially observable Markov decision processes and reinforcement learning for simulated robot navigation
LD Pyeatt - 1999 - search.proquest.com
This dissertation presents a two level architecture for goal-directed robot control. The low
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …
[PDF][PDF] INTEGRATION OF PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES AND REINFORCEMENT LEARNING FOR SIMULATED ROBOT …
LD Pyeatt - 1999 - Citeseer
This dissertation presents a two level architecture for goal-directed robot control. Reactivity,
deliberation, and learning are integral parts of the architecture. The low level actions are …
deliberation, and learning are integral parts of the architecture. The low level actions are …
Integration of partially observable Markov decision processes and reinforcement learning for simulated robot navigation.
LD Pyeatt - 2000 - elibrary.ru
This dissertation presents a two level architecture for goal-directed robot control. The low
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …
Integration of partially observable markov decision processes and reinforcement learning for simulated robot navigation
LD Pyeatt - 1999 - dl.acm.org
This dissertation presents a two level architecture for goal-directed robot control. The low
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …
level actions are learned on-line as the robot performs its tasks, thereby reducing the need …