我们为 MineRL 家族增加了一项新竞赛:BASALT,这是一项关于解决人工判断任务的竞赛,奖金为 11,000 美元。本次比赛中的任务没有预定义的奖励函数:目标是产生由真人判断可有效解决给定任务的轨迹。这对于 ML 社区来说是一个未知的领域,它将需要一套不同的规范和培训程序——也许将演示与现场人类排名、评级或比较的来源相结合,以指导代理朝着正确的方向前进。我们希望这场竞赛可以推动研究界建立这些新程序,随着我们希望人工智能系统融入我们生活的更多领域,我们预计这些程序将变得越来越重要。
与Diamond 比赛一样,BASALT 提供了一组与人类演示配对的 Gym 环境,因为基于模仿的方法是解决难以指定的任务的重要组成部分。
注册参加比赛: Sign-up to participate on [AIcrowd]!(好像需要科学上网)
The Tasks
FindCave
The agent should search for a cave, and terminate the episode when it is inside one.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732163-161069-caves4-1-47.gif)
MakeWaterfall
After spawning in a mountainous area, the agent should build a beautiful waterfall and then reposition itself to take a scenic picture of the same waterfall.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732227-410483-waterfall7-3-00.gif)
CreateVillageAnimalPen
After spawning in a village, the agent should build an animal pen containing two of the same kind of animal next to one of the houses in a village.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732245-503427-animal-pen-village3-0-05.gif)
BuildVillageHouse
Using items in its starting inventory, the agent should build a new house in the style of the village, in an appropriate location (e.g. next to the path through the village), without harming the village in the process.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732263-583095-house-long-1-00.gif)
Competition Overview
All submissions are through AIcrowd. There you can find detailed rules as well as the leaderboard.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732290-595600-image.png)
Submission: Submit Trained Agents
- Participants train agents to solve BASALT tasks. Participants submit both the training code as well as already-trained models for evaluation.
![](http://deeprlhub.com/assets/files/2021-07-08/1625732443-446446-image.png)
Baseline submission
Our baseline is a simple behavioral cloning algorithm trained for a couple of hours. We hope to see participants improve upon it significantly!
![](http://deeprlhub.com/assets/files/2021-07-08/1625732525-91912-image.png)
![](http://deeprlhub.com/assets/files/2021-07-08/1625732555-116323-image.png)