Author: 이동민 Date: February 25, 2019 Inverse RL 6번째 논문 Author : Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine Paper Link : https://arxiv.org/pdf/1810.00821.pdf Proceeding : International Conference of Learning Representations (ICLR) 2019 수정중.. VAIL Code GitHub - reinforcement-learning-kr/lets-do-irl: Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL) Inverse RL algorithms (A..
Author: 이승현 Date: February 13, 2019 Inverse RL 5번째 논문 Author : Jonathan Ho, Stefano Ermon Paper Link : https://papers.nips.cc/paper/6391-generative-adversarial-imitation-learning.pdf Proceeding : Advances in Neural Information Processing Systems (NIPS) 2016 0. Abstract 전문가의 시연으로부터 policy를 학습하는 문제를 해결하기 위해 사용되는 대표적인 imitation learning 방법으로는 먼저 inverse reinforcement learning으로 cost fuction을 복원하고, ..
Author: 이동민 Date: February 10, 2019 Inverse RL 4번째 논문 Author : Brian D. Ziebart, Andrew Maas, J.Andrew Bagnell, Anind K. Dey Paper Link : http://www.aaai.org/Papers/AAAI/2008/AAAI08-227.pdf Proceeding : Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence 2008 0. Abstract 2008년 당시의 최근 연구는 imitation learning의 문제를 Markov Decision Problems(MDP)로 해결함으로써 모방 학습에 대한 장점을 보였습니다. 이러한..
Author: 이동민 Date: February 7, 2019 Inverse RL 3번째 논문 Author : Nathan D. Ratliff, J. Andrew Bagnell, Martin A. Zinkevich Paper Link : https://www.ri.cmu.edu/pub_files/pub4/ratliff_nathan_2006_1/ratliff_nathan_2006_1.pdf Proceeding : International Conference on Machine Learning (ICML) 2006 0. Abstract 일반적으로 Supervised learning techniques를 통해 sequential, goal-directed behavior에 대한 imitation learnin..
