Prob_AI at the Interface of Reinforcement Learning & Evolutionary Biology 2027
22 April 2027 @ Warwick
Overview
Reinforcement Learning (RL) has emerged as a fundamental tool for the design of artificial agents possessing optimality and safety guarantees. A series of results has established that the behaviour learnt by RL agents interacting with one another can be understood using the tools of evolutionary game theory – for example, one can investigate conditions under which agents’ learnt policies converge to Evolutionarily Stable Strategies of the underlying game. Issues such as the emergence of cooperation, the tragedy of the commons, partner selection, population structure, and the exploration/exploitation trade-off are key questions in the study of both artificial intelligence and evolutionary biology and can be described using similar underlying mathematical frameworks. The aim of this workshop is to explore recent developments at this interface, to discuss open questions, and to bring together researchers from both communities.
This one-day workshop, in association with ProbAILink opens in a new window and CRiSMLink opens in a new window, will bring together researchers in reinforcement learning and in evolutionary game theory to share their research and to spark new interactions between these disciplines.
Confirmed speakers
- Mark Broom (City St George's)
- Tom Lenaerts (Université Libre de Bruxelles)
- Ann Nowé (Vrije Universiteit Brussel)
- Benedict Russell (University of Warwick)
Further speakers will be added here as they confirm.
Details
Date: 22 April, 2027
Venue: MB0.07, Mathematical Sciences BuildingLink opens in a new window (ground floor), University of Warwick, Coventry CV4 7AL, United Kingdom.
Programme: see Programme page
Registration: see Registration page
Local information: see Local Information page
Organising committee: Paul JenkinsLink opens in a new window, Benedict RussellLink opens in a new window, Kathrin SchütrumpfLink opens in a new window, James SykesLink opens in a new window, Paolo TurriniLink opens in a new window. To contact the organisers please use probai-rl-eb-workshop@googlegroups.com.
The Organising Committee gratefully acknowledges joint funding from the Centre for Research in Statistical Methodology (CRiSM) at Warwick statistics and Prob_AI Research Hub.