README.md

Awesome Inverse Reinforcement Learning/Imitation Learning

This is a collection of research papers for Inverse Reinforcement Learning (IRL) and Imitation Learning (IL). And the repository will be continuously updated to track the frontier of IRL & IL.

ICLR 2022

Cross-domain Imitation Learning via Optimal Transport

• Cross-Domain Imitation Learning via Optimal Transport

  • Arnaud Fickinger, Samuel Cohen, Stuart Russell, Brandon Amos
  • Keywords: optimal transportation, imitation learning, cross-domain imitation learning, gromov-Wasserstein

• DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations

  • Geon-Hyeong Kim, Seokin Seo, Jongmin Lee, Wonseok Jeon, HyeongJoo Hwang, Hongseok Yang, Kee-Eung Kim
  • Keywords: imitation learning, offline imitation learning, imperfect demonstration, non-expert demonstration

• Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

  • Quanyi Li, Zhenghao Peng, Bolei Zhou
  • Keywords: Human in the Loop, Safe Reinforcement Learning, Autonomous Driving

• Hierarchical Few-Shot Imitation with Skill Transition Models

  • Kourosh Hakhamaneshi, Ruihan Zhao, Albert Zhan, Pieter Abbeel, Michael Laskin
  • Keywords: behavioral priors, skill extraction, imitation learning, few-shot learning

• Imitation Learning by Reinforcement Learning

  • Kamil Ciosek
  • Keywords: reinforcement learning, imitation learning, Markov Decision Process, continuous control

• Imitation Learning from Observations under Transition Model Disparity

  • Tanmay Gangwani, Yuan Zhou, Jian Peng
  • Keywords: Imitation Learning, Deep Reinforcement Learning

• Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies

  • Alex Chan, Alicia Curth, Mihaela van der Schaar
  • Keywords: Decision Modelling, Imitation Learning, Inverse Online Learning

• Learning Value Functions from Undirected State-only Experience

  • Matthew Chang, Arjun Gupta, Saurabh Gupta
  • Keywords: Reinforcement Learning, Offline RL, Offline RL without actions

• Meta-Imitation Learning by Watching Video Demonstrations

  • Jiayi Li, Tao Lu, Xiaoge Cao, Yinghao Cai, Shuo Wang
  • Keywords: Meta-imitation Learning, One-shot Learning, Learning by Watching, Generative Adversarial Networks

• On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning

  • Guy Tennenholtz, Assaf Hallak, Gal Dalal, Shie Mannor, Gal Chechik, Uri Shalit
  • Keywords: imitation learning, reinforcement learning, expert data, hidden confounding, causal inference, covariate shift

• The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

  • Cassidy Laidlaw, Anca Dragan
  • Keywords: human model, boltzmann rationality, suboptimality, HRI, human-robot collaboration, generative models, reinforcement learning, deep RL

• TRAIL: Near-Optimal Imitation Learning with Suboptimal Data

  • Mengjiao Yang, Sergey Levine, Ofir Nachum
  • Keywords: Imitation Learning, Action Representations, Latent Dynamics Model, Offline Datasets