General Tree Evaluation for AlphaZero

Over the last decade, there have been significant advances in model-based deep reinforcement learning. One of the most successful such algorithms is AlphaZero which combines Monte Carlo Tree Search with deep learning. AlphaZero and its successors commonly describe a unified framework for tree construction and acting. For instance, build the tree...

A Hybrid Reinforcement Learning and Tree Search Approach for Network Topology Control

The growing demand for electricity, driven by widespread adoption of heat pumps, electric vehicles, and industrial electrification, strains power grids and introduces challenges for a reliable and secure supply amidst intermittent renewable energy integration. Network topology control offers flexibility, altering connections to redirect power...

Solving ML with ML: Evaluating the performance of the Monte Carlo Tree Search algorithm in the context of Program Synthesis

Machine learning pipelines encompass various sequential steps involved in tasks such as data extraction, preprocessing, model training, and deployment. Manual construction of these pipelines demands expert knowledge and can be time-consuming. To address this challenge, program synthesis offers an automated approach to generate computer programs...

Improvements in Monte Carlo Tree Search for Inductive Program Synthesis

A recent development in program synthesis is using Monte Carlo Tree Search to traverse the search tree of possible programs in order to efficiently find a program that will successfully transform the given input to the desired output. Previous research has shown promising results as Monte Carlo Tree Search is able to escape local optima that...

Inductive Program Synthesis through using Monte Carlo Tree Search guided by a heuristic-based loss function

Recently, a new and promising Inductive Program Synthesis (IPS) system, Brute, showed the potential of using a heuristic-based loss function. However, Brute also has its limitations and struggles with escaping local optima. The Monte Carlo Tree Search might offer a solution to this problem since it balances between exploitation and exploration....

Improving (ε,δ)-PAC Monte Carlo tree search using spherical confidence regions

We consider a simplified version of the Monte Carlo tree search (MCTS) problem, a problem where, given a game tree with stochastic reward, one is tasked with finding the best move from the root. This problem is well studied, and recently impressive results have been obtained. For example, in 2016, when the AlphaGo program beat the professional...

Constrained Multi-Aircraft Maintenance Scheduling Using Component Prognostics

In recent years, airlines have increasingly developed the ability to monitor the condition of aircraft components by means of sensors. In turn, aircraft maintenance aims to use this sensor data to predict component failures. However, the challenge remains to make use of these prognostics to generate appropriate maintenance schedules. In this...

Generalization and locality in the AlphaZero algorithm: A study in single agent, fully observable, deterministic environments

Recently, the AlphaGo algorithm has managed to defeat the top level human player in the game of Go. Achieving professional level performance in the game of Go has long been considered as an AI milestone. The challenging properties of high state-space complexity, long reward horizon and high action branching factor in the game of Go are also...

Bayesian Reinforcement Learning in Factored POMDPs

Model-based Bayesian Reinforcement Learning (BRL) provides a principled solution to dealing with the exploration-exploitation trade-off, but such methods typically assume a fully observable environments. The few Bayesian RL methods that are applicable in partially observable domains, such as the Bayes-Adaptive POMDP (BA-POMDP), scale poorly. To...

Action Selection Policies for Walking Monte Carlo Tree Search

Recent Reinforcement Learning methods have combined function approximation and Monte Carlo Tree Search and are able to learn by self-play up to a very high level in several games such as Go and Hex. One aspect in this combination<br/>that has not had a lot of attention is the action selection policy during self-play, which could influence the...