E-HBA: Using Action Policies for Expert Advice and Agent Typification
نویسندگان
چکیده
Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behaviour of other agents. In this work, we bring these complementary views together in the form of a novel meta-algorithm, called Expert-HBA (E-HBA), which can be applied to any expert algorithm that considers the average (or total) payoff an expert has yielded in the past. E-HBA gradually mixes the past payoff with a predicted future payoff, which is computed using the type-based characterisation. We present results from a comprehensive set of repeated matrix games, comparing the performance of several well-known expert algorithms with and without the aid of E-HBA. Our results show that E-HBA has the potential to significantly improve the performance of expert algorithms.
منابع مشابه
The effect of customer empowerment on adherence to expert advice☆
a r t i c l e i n f o Customers often receive expert advice related to their health, finances, taxes or legal procedures, to name just a few. A noble stance taken by some is that experts should empower customers to make their own decisions. In this article, we distinguish informational from decisional empowerment and study whether empowerment leads customers to adhere more or less to expert adv...
متن کاملPhysical activity advice only or structured exercise training and association with HbA1c levels in type 2 diabetes: a systematic review and meta-analysis.
CONTEXT Regular exercise improves glucose control in diabetes, but the association of different exercise training interventions on glucose control is unclear. OBJECTIVE To conduct a systematic review and meta-analysis of randomized controlled clinical trials (RCTs) assessing associations of structured exercise training regimens (aerobic, resistance, or both) and physical activity advice with ...
متن کاملUsing Advice in Model-Based Reinforcement Learning
When a human is mastering a new task, they are usually not limited to exploring the environment, but also avail themselves of advice from other people. In this paper, we consider the use of advice expressed in a formal language to guide exploration in a model-based reinforcement learning algorithm. In contrast to constraints, which can eliminate optimal policies if they are not sound, advice is...
متن کاملCounterfactual Exploration for Improving Multiagent Learning
In any single agent system, exploration is a critical component of learning. It ensures that all possible actions receive some degree of attention, allowing an agent to converge to good policies. The same concept has been adopted by multiagent learning systems. However, there is a fundamentally different dynamic in multiagent learning: each agent operates in a non-stationary environment, as a d...
متن کاملObject-Focused Advice in Reinforcement Learning
In order for robots and intelligent agents to interact with and learn from people with no machine-learning expertise, robots should be able to learn from natural human instruction. Many human explanations consist of simple sentences without state information, yet most machine learning techniques that incorporate human guidance cannot use nonspecific explanations. This work aims to learn policie...
متن کامل