Search
Now showing items 1-3 of 3
Inferring dependencies in Embodiment-based modular reinforcement learning
(2005)
The state-spaces needed to describe realistic--physical embodied agents are extremely large, which presents a serious challenge to classical einforcement learning schemes. In previous work--(Jacob et al., 2005a, Jacob et ...
Legs that can walk: Embodiment-Based Modular Reinforcement Learning applied
(Institute of Electrical and Electronics Engineers (IEEE), 2005)
Experiments to illustrate a novel methodology for reinforcement learning in embodied physical agents are described. A simulated legged robot is decomposed into structurebased modules following the authors' EMBER principles ...