Interactive Teaching Strategies for Agent Training

By Ofra Amir, Ece Kamar, Andrey Kolobov, B. Grosz. 2016

116 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.

Citations in the corpus

Leveraging Human Guidance for Deep Reinforcement Learning Tasks (2019, background): “Amir et al. [ 2016 ] studied human attention limits while monitoring the learning process of an agent and proposed an algorithm for the human and the agent to jointly identify states where feedback is most needed to reduce human monitoring cost.”
Learning Hierarchical Teaching Policies for Cooperative Agents (2019, background): “ts Q-values and the difference between the student’s intended action and teacher’s intended action at a student state. Note that AICI is one of the best performing heuristic algorithms in Amir et al. [1]. Hierarchical AI (HAI) and hierarchical AICI (HAICI) are similar to AI and AICI, but teach in th”
Agent-Agnostic Human-in-the-Loop Reinforcement Learning (2017, background): “The agent is not specialized to the protocol, so it is unable to ask the human informative questions as in [4], or will not have an observation model that faithfully represents the process the human uses to generate advice, as in [17, 21].”
A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint (2020, background): “There have been three modes of deciding the advising opportunities: student-initiated [29], teacher-initiated [4] and jointly-initiated [30].”
Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning (2020, background): “mainly concern with the student’s decision value, such as Ask Uncertain [14] and Ask Important [15].”