Papers of the day   All papers

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Comments

Ian Osband: This feels like a real breakthrough: https://arxiv.org/abs/1911.08265 Take the same basic algorithm as AlphaZero, but now *learning* its own simulator. Beautiful, elegant approach to model-based RL. ... AND ALSO STATE OF THE ART RESULTS! Well done to the team at @DeepMindAI #MuZero

5 replies, 806 likes


Brandon Rohrer: I hope that MuZero, the latest work by @DeepMindAI, sets a trend for model learning in RL. It’s a powerful and largely unexplored middle ground between model-based and model-free RL. https://arxiv.org/pdf/1911.08265.pdf https://t.co/gj3n8qxgGs

0 replies, 140 likes


Mark O. Riedl: MuZero (DeepMind) gets top performance on 57 different Atari games and matches the performance of AlphaZero in Go, chess, and shogi https://arxiv.org/abs/1911.08265 Does so without knowing the rules of the game, which it learns using model-based RL

1 replies, 125 likes


Ankesh Anand: Exciting new paper from @DeepMindAI : Planning with **learned** models can scale to complex visual domains like Atari. TL;DR: MCTS + Q-learning with models that only predict rewards/Q-values leads to new SOTA on Atari games and matches AlphaZero on Go. https://arxiv.org/abs/1911.08265 https://t.co/d961KoFiiy

0 replies, 102 likes


Noam Brown: "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" -- Really exciting new work from the AlphaZero group at DeepMind! https://arxiv.org/abs/1911.08265

1 replies, 83 likes


Pascal Bornet: New @DeepMind's #MuZero wins at games WITHOUT prior knowledge of their rules https://arxiv.org/abs/1911.08265 #AI @alvinfoo @kashthefuturist @FrRonconi @Paula_Piccard @ronald_vanloon @jblefevre60 @evankirstel @mvollmer1 @HeinzvHoenen @samiranghosh @YuHelenYu @MHiesboeck @andy_lucerne https://t.co/wgAiejEyEa

1 replies, 71 likes


Thomas G. Dietterich: I enjoyed reading this paper. Many nice design choices. I have some questions that mayydolks can answer. First, how hard is it to learn a really good transition model for chess? For go?

4 replies, 60 likes


Adam Santoro: Another incredible step to make AlphaZero even more general, doing away with the simulator and instead embedding it in the learning loop. In before "but it still uses a highly structured tree search!"

6 replies, 44 likes


Rob Miles: MuZero, the latest from Deepmind, can play Chess, Go, Shogi *and Atari*. I don't see a straight line from here to AGI, but it is remarkable how these systems keep getting more and more general. https://arxiv.org/abs/1911.08265

4 replies, 39 likes


mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://arxiv.org/abs/1911.08265 😲

1 replies, 38 likes


Kaixhin: Alright, had to have a look at @DeepMindAI's SotA #MuZero: https://arxiv.org/abs/1911.08265 . AlphaZero, but with a learned model, leveraging good targets and predicting the policy, value and reward for rollouts to train representation, dynamics and prediction modules.

3 replies, 33 likes


Károly Zsolnai-Fehér 📜: MuZero: DeepMind’s New AI Mastered More Than 50 Games ▶️Full video (ours): https://youtu.be/hYV4-m7_SK8 📜Source paper: https://arxiv.org/abs/1911.08265 #ai #deeplearning #science #twominutepapers https://t.co/YfLYYOmYni

0 replies, 32 likes


Carlos E. Perez 🧢: DeepMind is so ahead of the curve. I was dreaming last night on a novel way to formulate an RL solution. Only find out this morning, that DeepMind implemented my dream and has a paper out! https://arxiv.org/abs/1911.08265 .

2 replies, 29 likes


Darshan H Sheth ✨ @Iamdarshan: New @DeepMind's #MuZero wins at games WITHOUT prior knowledge of their rules https://arxiv.org/abs/1911.08265 #AI @pascal_bornet @darshan_h_sheth @alvinfoo @kashthefuturist @FrRonconi @Paula_Piccard @ronald_vanloon @evankirstel @mvollmer1 @HeinzVHoenen https://t.co/fLfMBYNDvP

0 replies, 28 likes


Simon Osindero: Agreed — this is great progress!

1 replies, 17 likes


Santiago Ontañón: Man, one day not paying attention and I am already outdated! I was the only one not aware of DeepMind's MuZero in a discussion today! In case you also missed it: https://arxiv.org/pdf/1911.08265.pdf

2 replies, 13 likes


Daisuke Okanohara: MuZero improves AlphaZero by using a learned simulator, which is trained for predicting reward, value, and policy only, Achieved new SoTA on Atari, Model-based RL surpassing model-free for the first time, and mastered Shogi and Go without the game rules. https://arxiv.org/abs/1911.08265

0 replies, 8 likes


Aran Komatsuzaki: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://arxiv.org/abs/1911.08265 MuZero combines a tree-based search with a learned model and achieves superhuman performance, without knowledge of dynamics, at various games, including Go and Atari (sota).

0 replies, 8 likes


Shyamal S. Chandra ❤️♟️, 🐻, 🖥️, : @zacharylipton Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://arxiv.org/pdf/1911.08265.pdf @DeepMindAI

0 replies, 6 likes


Pierre Richemond: MuZero - MCTS on Atari, chess-Go, SotA, !! no knowledge of game rules or environment dynamics required !! Key paper. https://arxiv.org/abs/1911.08265

0 replies, 5 likes


Statistics Papers: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. http://arxiv.org/abs/1911.08265

0 replies, 5 likes


Rob The Quant: Algo by @Mononofu can generalize and achieves superhuman performance in 50+ games 👍 Paper at https://arxiv.org/pdf/1911.08265.pdf #AI #MachineLearning #ArtificialIntelligence https://t.co/xjSLGiTFsq

0 replies, 5 likes


Brundage Bot: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. Schrittwieser, Antonoglou, Hubert, Simonyan, Sifre, Schmitt, Guez, Lockhart, Hassabis, Graepel, Lillicrap, and Silver http://arxiv.org/abs/1911.08265

1 replies, 4 likes


TojoHQ: A new AI mastered Shogi and over 50 other games, and all I want to know is when we can use it to get our minigame trophies on the Yakuza games. PS: no, it can't play Mahjong yet.

0 replies, 4 likes


Eric Xu, PhD (徐宥) 🧢: Holy Cow this is a good step towards AGI. https://arxiv.org/abs/1911.08265

1 replies, 4 likes


Dan Hughes: MuZero learned to play 60 games at superhuman levels without knowing their rules. MZ predicts the quantities most directly relevant to planning: the reward, the action-selection policy, and the value functions. https://arxiv.org/abs/1911.08265

1 replies, 3 likes


Haruhiko Okumura: "When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules." https://arxiv.org/abs/1911.08265 Wow!

0 replies, 3 likes


Jonathan Raiman: Incredible work on Model-based RL that finally outperforms other approaches on both continuous/visual games (Atari) and board games (go, chess, shogu) from @DeepMindAI @Mononofu, Antonoglou, Hubert et al. So many problems can be cast this way, congrats! https://arxiv.org/abs/1911.08265

0 replies, 2 likes


Barney Pell: Wow!!

0 replies, 2 likes


Federico Andres Lois: A new year, a new AlphaZero paper. Muzero now in model-free flavour without losing capability. #reinforcementlearning https://arxiv.org/abs/1911.08265

0 replies, 2 likes


風凪空@幻想邪神(幻月の夫): @pc_user_walker https://twitter.com/kazanagisora/status/1075740711847452672 https://twitter.com/kazanagisora/status/1198926382727778305

1 replies, 1 likes


Yohan J. Rodríguez: #Tech #Automated | Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://arxiv.org/abs/1911.08265?utm_source=hackernewsletter&utm_medium=email&utm_term=data

0 replies, 1 likes


Content

Found on Nov 21 2019 at https://arxiv.org/pdf/1911.08265.pdf

PDF content of a computer science paper: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model