Real-world tasks of interest are generally poorly defined by human-readable descriptions and have no pre-defined reward signals unless it is defined by a human designer. Conversely, data-driven algorithms are often designed to solve a specific, narrowly defined, task with performance metrics that drives the agent's learning. In this work, we present the solution that won first place and was awarded the most human-like agent in the 2021 NeurIPS Competition MineRL BASALT Challenge: Learning from Human Feedback in Minecraft, which challenged participants to use human data to solve four tasks defined only by a natural language description and no reward function. Our approach uses the available human demonstration data to train an imitation learning policy for navigation and additional human feedback to train an image classifier. These modules, combined with an estimated odometry map, become a powerful state-machine designed to utilize human knowledge in a natural hierarchical paradigm. We compare this hybrid intelligence approach to both end-to-end machine learning and pure engineered solutions, which are then judged by human evaluators. Codebase is available at https://github.com/viniciusguigo/kairos_minerl_basalt.
Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations
Artificial Intelligence Research Institute FRC CSC RAS（俄罗斯科学院计算机科学与控制研究中心人工智能研究所）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Higher School of Economics（高等经济学院）；Moscow Aviation Institute（莫斯科航空学院）
A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction
Department of Electronic Engineering, Wonkwang University（圆光大学电子工程系）；AI Convergence Research Institute, Wonkwang University（圆光大学人工智能融合研究院）；GIST InnoCORE AI-Nano Convergence Institute for Early Detection of Neurodegenerative Diseases, Gwangju Institute of Science and Technology（光州科学技术院GIST InnoCORE AI-Nano神经退行性疾病早期检测融合研究所）；School of Electrical Engineering, KAIST（韩国科学技术院电气工程学院）；Department of AI Convergence, Gwangju Institute of Science and Technology（光州科学技术院人工智能融合系）
Hierarchical Bayesian Modelling for Knowledge Transfer Across Engineering Fleets via Multitask Learning
The Alan Turing Institute（艾伦·图灵研究所）；University of Cambridge（剑桥大学）；Scania CV（斯堪尼亚商用车公司）；Scania AB (publ)（斯堪尼亚公司（上市））；Stockholm University（斯德哥尔摩大学）；Imperial College London（伦敦帝国理工学院）
Explainable AI for Engineering Design: A Unified Approach of Systems Engineering and Component- Based Deep Learning Demonstrated by Energy- Efficient Building Design
Leibniz University Hannover（汉诺威莱布尼茨大学）；Technical University of Munich（慕尼黑工业大学）
