Journal ArticleDOI
Solving the Rubik’s cube with deep reinforcement learning and search
TLDR
A new deep learning based search heuristic performs well on the iconic Rubik’s cube and can also generalize to puzzles in which optimal solvers are intractable.Abstract:
The Rubik’s cube is a prototypical combinatorial puzzle that has a large state space with a single goal state. The goal state is unlikely to be accessed using sequences of randomly generated moves, posing unique challenges for machine learning. We solve the Rubik’s cube with DeepCubeA, a deep reinforcement learning approach that learns how to solve increasingly difficult states in reverse from the goal state without any specific domain knowledge. DeepCubeA solves 100% of all test configurations, finding a shortest path to the goal state 60.3% of the time. DeepCubeA generalizes to other combinatorial puzzles and is able to solve the 15 puzzle, 24 puzzle, 35 puzzle, 48 puzzle, Lights Out and Sokoban, finding a shortest path in the majority of verifiable cases. For some combinatorial puzzles, solutions can be verified to be optimal, for others, the state space is too large to be certain that a solution is optimal. A new deep learning based search heuristic performs well on the iconic Rubik’s cube and can also generalize to puzzles in which optimal solvers are intractable.read more
Citations
More filters
Posted Content
Model-based Reinforcement Learning: A Survey
TL;DR: A survey of the integration of model-based reinforcement learning and planning, better known as model- based reinforcement learning, and a broad conceptual overview of planning-learning combinations for MDP optimization are presented.
Journal ArticleDOI
Topological Quantum Compiling with Reinforcement Learning.
TL;DR: An efficient algorithm based on deep reinforcement learning that compiles an arbitrary single-qubit gate into a sequence of elementary gates from a finite universal set is introduced, which generates near-optimal gate sequences with given accuracy.
Journal ArticleDOI
A Fortran-Keras Deep Learning Bridge for Scientific Computing
TL;DR: A software library, the Fortran-Keras Bridge (FKB), which connects environments where deep learning resources are plentiful, with those where they are scarce and reveals many neural network architectures that produce considerable improvements in stability including some with reduced error, for an especially challenging training dataset.
Posted Content
Automated curricula through setter-solver interactions.
Sébastien Racanière,Andrew K. Lampinen,Adam Santoro,David P. Reichert,Vlad Firoiu,Timothy P. Lillicrap +5 more
TL;DR: These results represent a substantial step towards applying automatic task curricula to learn complex, otherwise unlearnable goals, and are the first to demonstrate automated curriculum generation for goal-conditioned agents in environments where the possible goals vary between episodes.
Posted Content
A Fortran-Keras Deep Learning Bridge for Scientific Computing
TL;DR: The Fortran-Keras Bridge (FKB) as discussed by the authors enables a hyperparameter search of one hundred plus candidate models of subgrid cloud and radiation physics, initially implemented in Keras, to be transferred and used in Fortran.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Posted Content
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Batch Normalization as mentioned in this paper normalizes layer inputs for each training mini-batch to reduce the internal covariate shift in deep neural networks, and achieves state-of-the-art performance on ImageNet.
Journal ArticleDOI
Deep learning in neural networks
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Related Papers (5)
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more