Abstraction can improve the sample efficiency of reinforcement learning. However, the
process of abstraction inherently discards information, potentially compromising an agent's …

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs)
is that the relevant decision process is, in fact, Markov. However, when MDPs have rich …

Today's automated vehicles lack the ability to cooperate implicitly with others. This work
presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative …

In order to solve complex, long-horizon tasks, intelligent robots need to carry out high-level,
abstract planning and reasoning in conjunction with motion planning. However, abstract …

We propose a novel reinforcement learning algorithm, AlphaNPI, that incorpo-rates the
strengths of Neural Programmer-Interpreters (NPI) and AlphaZero. NPI contributes structural …

The ability of a robot to plan complex behaviors with real-time computation, rather than
adhering to predesigned or offline-learned routines, alleviates the need for specialized …

The fundamental concept behind option-based hierarchical reinforcement learning (O-HRL)
is to obtain temporal coarse-grained actions and abstract complex situations. Although O …

In many real-world problems, the learning agent needs to learn a problem's abstractions and
solution simultaneously. However, most such abstractions need to be designed and refined …

Abstract Monte Carlo Tree Search (MCTS) algorithms such as AlphaGo and MuZero have
achieved superhuman performance in many challenging tasks. However, the computational …

Robots operating in households must find objects on shelves, under tables, and in
cupboards. In such environments, it is crucial to search efficiently at 3D scale while co** …