홈 › Papers

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

2021-01-26 · 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. 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.

📄 PDF Abstract BibTeX arXiv:2101.11071

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Reinforcement LearningEfficient ExplorationMinecraftreinforcement-learning Reinforcement Learning (RL)Sequential Decision Making

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

2020-03-10 · Stephanie Milani, Nicholay Topin, Brandon Houghton, William H. Guss 외

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 In…

Deep Reinforcement Learning Imitation Learning reinforcement-learning Reinforcement Learning+1

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

2019-04-22 · William H. Guss, Cayden Codel, Katja Hofmann, Brandon Houghton 외

Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require a…

Decision Making Deep Reinforcement Learning Efficient Exploration Minecraft+4

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

2021-11-17 · Hangyu Mao, Chao Wang, Xiaotian Hao, Yihuan Mao 외

The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment intera…

Imitation Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

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

2022-02-17 · Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin 외

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers n…

Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft

2020-03-12 · Christian Scheller, Yanick Schraner, Manfred Vogel

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minec…

Deep Reinforcement Learning Minecraft reinforcement-learning Reinforcement Learning+1