The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
By William H. Guss, Cayden R. Codel, Katja Hofmann, Brandon Houghton, Noburu Kuno, Stephanie Milani, Sharada Prasanna Mohanty, Diego Perez Liebana, Ruslan Salakhutdinov, Nicholay Topin and 2 more. 2021
73 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Abhinav Kumar Gupta
- Pieter Abbeel
- Mohit Bansal
- Ruslan Salakhutdinov
- Yoshua Bengio
- Jianfeng Gao
- Quoc V. Le
Citations in the corpus
- Dota 2 with Large Scale Deep Reinforcement Learning (2019, background): “In recent years, reinforcement learning (RL) models have tackled tasks as varied as robotic manipulation[5], text summarization [6], and video games such as Starcraft[7] and Minecraft[8].”
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge (2022, methodology): “In comparison, the NeurIPS MineRL Diamond challenge [48] is a subset of our programmatic task suite, defined by the task goal “obtain 1 diamond" in MINEDOJO.”
- CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, background): “RL is also frequently evaluated on video game-like environments, most commonly Atari [3], among others [9, 8, 70, 2, 25, 23, 17, 10, 34].”