Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Abstract. Reasoning plays a central role in intelligent systems that operate in complex situations that involve time constraints. In this paper, we present the Adaptive Logic Inter...
Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachi...
— In this paper, we present a novel approach to controlling a robotic system online from scratch based on the reinforcement learning principle. In contrast to other approaches, o...
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sug...