Multi-Advisor Reinforcement Learning

2017-04-03 · ICLR 2018 1 · Romain Laroche, Mehdi Fatemi, Joshua Romoff, Harm van Seijen

We consider tackling a single-agent RL problem by distributing it to $n$ learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their advice, taking the form of action values, is then communicated to an aggregator, which is in control of the system. We show that the local planning method for the advisors is critical and that none of the ones found in the literature is flawless: the egocentric planning overestimates values of states where the other advisors disagree, and the agnostic planning is inefficient around danger zones. We introduce a novel approach called empathic and discuss its theoretical aspects. We empirically examine and validate our theoretical findings on a fruit collection task.

📄 PDF Abstract BibTeX arXiv:1704.00756

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning

2023-01-26 · Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley

Multi-agent reinforcement learning typically suffers from the problem of sample inefficiency, where learning suitable policies involves the use of many data samples. Learning from external demonstrators is a possible sol…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Multi-Agent Advisor Q-Learning

2021-10-26 · Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley

In the last decade, there have been significant advances in multi-agent reinforcement learning (MARL) but there are still numerous challenges, such as high sample complexity and slow convergence to stable policies, that …

Decision Making Multi-agent Reinforcement Learning Q-Learning reinforcement-learning+1

Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning

2020-07-23 · Frédéric Logé, Erwan Le Pennec, Habiboulaye Amadou-Boubacar

Patients with diabetes who are self-monitoring have to decide right before each meal how much insulin they should take. A standard bolus advisor exists, but has never actually been proven to be optimal in any sense. We c…

reinforcement-learning Reinforcement Learning (RL)

Bridging the Imitation Gap by Adaptive Insubordination

2020-07-23 · NeurIPS 2021 12 · Luca Weihs, Unnat Jain, Iou-Jen Liu, Jordi Salvador 외

In practice, imitation learning is preferred over pure reinforcement learning whenever it is possible to design a teaching agent to provide expert supervision. However, we show that when the teaching agent makes decision…

Imitation Learning Memorization reinforcement-learning Reinforcement Learning+1

Hindsight Preference Optimization for Financial Time Series Advisory

2026-04-27 · Yanwei Cui, Guanghui Wang, Xing Zhang, Peiyang He 외 arxiv

Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management. Training language models for such predictive advisory faces a fundamen…

Reinforcement Learning