Policy Shaping with Human Teachers

91 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation (2020, background): “Loftin et al. speed up learning by adapting to different feedback-providing strategies [23, 24]; the Advice framework [11, 6] treats human feedback as direct policy labels and uses a probabilistic model to learn from inconsistent feedback.”
Deep Q-learning From Demonstrations (2017, methodology): “A different approach is to shape the policy that is used to sample experience (Cederborg et al. 2015), or to use policy iteration from demonstrations (Kim et al.”
Leveraging Human Guidance for Deep Reinforcement Learning Tasks (2019, methodology): “The nature of the feedback could potentially vary across tasks and trainers [ Loftin et al. , 2016 ] , and can be altered by instruction given to the trainers [ Cederborg et al. , 2015 ] .”
Learning from Demonstrations for Real World Reinforcement Learning (2017, methodology): “A different approach is to shape the policy that is used to sample experience Cederborg et al. (2015), or to use policy iteration from demonstrations Kim et al. (2013); Chemali & Lezaric (2015).”
Interactive reinforcement learning for task-oriented dialogue management (2016, background): “Cederborg et al. (2015) present experimental results of applying this approach with human teachers, showing that the assumptions made by the policy shaping algorithm about human teachers are reasonable.”