Differential Advising In Multi-agent Reinforcement Learning

Abstract

Agent advising is one of the main approaches to improve agent learning performance by enabling agents to share advice. Existing advising methods have a common limitation that an adviser agent can offer advice to an advisee agent only if the advice is created in the same state as the advisee's concerned state. However, in complex environments, it is a very strong requirement that two states are the same, because a state may consist of multiple dimensions and two states being the same means that all these dimensions in the two states are correspondingly identical. Therefore, this requirement may limit the applicability of existing advising methods to complex environments. In this paper, inspired by the differential privacy scheme, we propose a differential advising method which relaxes this requirement by enabling agents to use advice in a state even if the advice is created in a slightly different state. Compared with existing methods, agents using the proposed method have more opportun

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyye2020differential

Related papers

• Learning From Multiple Independent Advisors In Multi-agent Reinforcement Learning (2023)0.00
• Agent-aware Training For Agent-agnostic Action Advising In Deep Reinforcement Learning (2023)2.26
• Explainable Action Advising For Multi-agent Reinforcement Learning (2022)6.77
• Multi-agent Advisor Q-learning (2021)0.00
• Learning To Advise And Learning From Advice In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84
• Shaping Advice In Deep Reinforcement Learning (2022)0.00
• Theoretically-grounded Policy Advice From Multiple Teachers In Reinforcement Learning Settings With Applications To Negative Transfer (2016)0.00