28th International Conference on Machine Learning, ICML 2011 465–472 (Omnipress, 2011). PILCO: a model-based and data-efficient approach to policy search. Reinforcement Learning: An Introduction 2nd edn (MIT Press, 2018).ĭeisenroth, M. Planning chemical syntheses with deep neural networks and symbolic AI. Planning and Scheduling Technical Report (EETN, 2013). Deepstack: expert-level artificial intelligence in heads-up no-limit poker. Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. A world championship caliber checkers program.
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play.
Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. The arcade learning environment: an evaluation platform for general agents. Mastering the game of Go with deep neural networks and tree search. When evaluated on Go, chess and shogi-canonical environments for high-performance planning-the MuZero algorithm matched, without any knowledge of the game dynamics, the superhuman performance of the AlphaZero algorithm 5 that was supplied with the rules of the game.Ĭampbell, M., Hoane, A. When evaluated on 57 different Atari games 3-the canonical video game environment for testing artificial intelligence techniques, in which model-based planning approaches have historically struggled 4-the MuZero algorithm achieved state-of-the-art performance. The MuZero algorithm learns an iterable model that produces predictions relevant to planning: the action-selection policy, the value function and the reward. Here we present the MuZero algorithm, which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. However, in real-world problems, the dynamics governing the environment are often complex and unknown.
MASTER THE BOARDS STEP 3 2019 SIMULATOR
Tree-based planning methods have enjoyed huge success in challenging domains, such as chess 1 and Go 2, where a perfect simulator is available. Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence.
0 kommentar(er)
