Robert William Wright

Learn More
Reinforcement learning (RL) is designed to learn optimal control policies from unsupervised interactions with the environment. Many successful RL algorithms have been developed, however, none of them can efficiently tackle problems with high-dimensional state spaces due to the "curse of dimensionality," and so their applicability to real-world scenarios is(More)
Approximate value iteration methods for reinforcement learning (RL) generalize experience from limited samples across large state-action spaces. The function approximators used in such methods typically introduce errors in value estimation which can harm the quality of the learned value functions. We present a new batch-mode, off-policy, approximate value(More)
High-frequency, thickness mode resonators were fabricated using a 7 microm piezoelectric transducer (PZT) thick film that was produced using a modified composite ceramic sol-gel process. Initial studies dealt with the integration of the PZT thick film onto the substrate. Zirconium oxide (ZrO2) was selected as a diffusion barrier layer and gave good results(More)