The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

no code implementations • 26 Jan 2021 • William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals

Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.

Decision Making Efficient Exploration +2

Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning

no code implementations • 10 Mar 2020 • Stephanie Milani, Nicholay Topin, Brandon Houghton, William H. Guss, Sharada P. Mohanty, Keisuke Nakata, Oriol Vinyals, Noboru Sean Kuno

To facilitate research in the direction of sample efficient reinforcement learning, we held the MineRL Competition on Sample Efficient Reinforcement Learning Using Human Priors at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019).

Imitation Learning reinforcement-learning +1

On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps

no code implementations • 3 Oct 2019 • William H. Guss, Ruslan Salakhutdinov

Additionally, we provide the first lower-bound on the minimal number of input and output units required by a finite approximation to an infinite neural network to guarantee that it can uniformly approximate any nonlinear operator using samples from its inputs and outputs.

Open-Ended Question Answering

MineRL: A Large-Scale Dataset of Minecraft Demonstrations

1 code implementation • 29 Jul 2019 • William H. Guss, Brandon Houghton, Nicholay Topin, Phillip Wang, Cayden Codel, Manuela Veloso, Ruslan Salakhutdinov

Therefore, we introduce a comprehensive, large-scale, simulator-paired dataset of human demonstrations: MineRL.

Benchmarking reinforcement-learning +1

The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors

1 code implementation • 22 Apr 2019 • William H. Guss, Cayden Codel, Katja Hofmann, Brandon Houghton, Noboru Kuno, Stephanie Milani, Sharada Mohanty, Diego Perez Liebana, Ruslan Salakhutdinov, Nicholay Topin, Manuela Veloso, Phillip Wang

To that end, we introduce: (1) the Minecraft ObtainDiamond task, a sequential decision making environment requiring long-term planning, hierarchical control, and efficient exploration methods; and (2) the MineRL-v0 dataset, a large-scale collection of over 60 million state-action pairs of human demonstrations that can be resimulated into embodied trajectories with arbitrary modifications to game state and visuals.

Decision Making Efficient Exploration +2

On Characterizing the Capacity of Neural Networks using Algebraic Topology

no code implementations • ICLR 2018 • William H. Guss, Ruslan Salakhutdinov

The learnability of different neural architectures can be characterized directly by computable measures of data complexity.

Inductive Bias

Deep Function Machines: Generalized Neural Networks for Topological Layer Expression

no code implementations • ICLR 2018 • William H. Guss

In this paper we propose a generalization of deep neural networks called deep function machines (DFMs).