Abstract Monte-Carlo Tree Search, especially UCT and its POMDP version POMCP, have
demonstrated excellent performanceon many problems. However, to efficiently scale to …

Cooperative reinforcement learning algorithms such as BEST-Q, AVE-Q, PSO-Q, and WSS
use Q-value sharing strategies between reinforcement learners to accelerate the learning …

We propose a model-based approach to hierarchical reinforcement learning that exploits
shared knowledge and selective execution at different levels of abstraction, to efficiently …

Efficient object manipulation based only on force feedback typically requires a plan of
actively contact-seeking actions to reduce uncertainty over the true environmental model. In …

In this paper, we propose to use hierarchical action decomposition to make Bayesian model-
based reinforcement learning more efficient and feasible for larger problems. We formulate …

Recent successes in Reinforcement Learning have encouraged a fast-growing network of
RL researchers and a number of breakthroughs in RL research. As the RL community and …

Reinforcement learning (RL) is an area of machine learning that is concerned with how an
agent learns to make decisions sequentially in order to optimize a particular performance …

We propose a model-based approach to hierarchical reinforcement learning that exploits
shared knowledge and selective execution at different levels of abstraction, to efficiently …

Abstract We present ASD (Action, Sequence, and Divide), a new framework for Hierarchical
Reinforcement Learning (HRL). Present HRL methods construct the task hierarchies but fail …

Reinforcement learning (RL) is a well-known class of machine learning algorithms used in
planning and controlling of autonomous agents. Most of the issues in planning and …