Search Results for author: Alexandre Borges

Found 2 papers, 0 papers with code

Combining Off and On-Policy Training in Model-Based Reinforcement Learning

no code implementations24 Feb 2021 Alexandre Borges, Arlindo Oliveira

Recently, MuZero demonstrated that it is possible to master both Atari games and board games by directly learning a model of the environment, which is then used with MCTS to decide what move to play in each position.

Atari Games Board Games +3

Cannot find the paper you are looking for? You can Submit a new open access paper.