Skip to content
conftrace_

adversarial inverse reinforcement learning

3 papers

Explore in graph

Also known as

AIRL

Co-occurring keywords · papers mentioning both

transition policy (1) multi-domain dialog (1) dialog policy (1) task-oriented dialog (1) deep q-learning (1) traffic signal control (1) reward estimation (1) reward function (1) distribution matching (1) hierarchical reinforcement learning (1)

Papers

InitLight: Initial Model Generation for Traffic Signal Control Using Adversarial Inverse Reinforcement Learning IJCAI 2023 Training Transition Policies via Distribution Matching for Complex Tasks ICLR 2022 Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog EMNLP 2019