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

01/26/2021
by   William H. Guss, et al.
11

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. Resolution of these limitations requires new, sample-efficient methods. To facilitate research in this direction, we propose this second iteration of the MineRL Competition. The primary goal of the competition is to foster the development of algorithms which can efficiently leverage human demonstrations to drastically reduce the number of samples needed to solve complex, hierarchical, and sparse environments. To that end, participants compete under a limited environment sample-complexity budget to develop systems which solve the MineRL ObtainDiamond task in Minecraft, a sequential decision making environment requiring long-term planning, hierarchical control, and efficient exploration methods. The competition is structured into two rounds in which competitors are provided several paired versions of the dataset and environment with different game textures and shaders. At the end of each round, competitors submit containerized versions of their learning algorithms to the AIcrowd platform where they are trained from scratch on a hold-out dataset-environment pair for a total of 4-days on a pre-specified hardware platform. In this follow-up iteration to the NeurIPS 2019 MineRL Competition, we implement new features to expand the scale and reach of the competition. In response to the feedback of the previous participants, we introduce a second minor track focusing on solutions without access to environment interactions of any kind except during test-time. Further we aim to prompt domain agnostic submissions by implementing several novel competition mechanics including action-space randomization and desemantization of observations and actions.

READ FULL TEXT

page 4

page 6

page 9

page 14

research
04/22/2019

The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors

Though deep reinforcement learning has led to breakthroughs in many diff...
research
03/10/2020

The MineRL Competition on Sample-Efficient Reinforcement Learning Using Human Priors: A Retrospective

To facilitate research in the direction of sample-efficient reinforcemen...
research
11/17/2021

SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition

The MineRL competition is designed for the development of reinforcement ...
research
06/07/2021

Towards robust and domain agnostic reinforcement learning competitions

Reinforcement learning competitions have formed the basis for standard r...
research
02/17/2022

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Reinforcement learning competitions advance the field by providing appro...
research
07/29/2019

MineRL: A Large-Scale Dataset of Minecraft Demonstrations

The sample inefficiency of standard deep reinforcement learning methods ...
research
05/07/2020

Playing Minecraft with Behavioural Cloning

MineRL 2019 competition challenged participants to train sample-efficien...

Please sign up or login with your details

Forgot password? Click here to reset