693 citations · 3.6k across the 81 of their papers we have counts for
10 papers · 1 filter
Malthusian Reinforcement Learning
Joel Z. Leibo, Julien Perolat, Edward Hughes +6
Here we explore a new algorithmic framework for multi-agent reinforcement learning, called Malthusian reinforcement learning, which extends self-play to include fitness-linked popu…
Evolving intrinsic motivations for altruistic behavior
Jane X. Wang, Edward Hughes, Chrisantha Fernando +3
Multi-agent cooperation is an important feature of the natural world. Many tasks involve individual incentives that are misaligned with the common good, yet a wide range of organis…
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
Natasha Jaques, Angeliki Lazaridou, Edward Hughes +5
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over…
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning +15
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based g…
Emergent Communication through Negotiation
Kris Cao, Angeliki Lazaridou, Marc Lanctot +3
Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the eme…
Unsupervised Predictive Memory in a Goal-Directed Agent
Greg Wayne, Chia-Chun Hung, David Amos +21
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of import…
A Generalised Method for Empirical Game Theoretic Analysis
Karl Tuyls, Julien Perolat, Marc Lanctot +2
This paper provides theoretical bounds for empirical game theoretical analysis of complex multi-agent interactions. We provide insights in the empirical meta game showing that a Na…
Kickstarting Deep Reinforcement Learning
Simon Schmitt, Jonathan J. Hudson, Augustin Zidek +8
We present a method for using previously-trained 'teacher' agents to kickstart the training of a new 'student' agent. To this end, we leverage ideas from policy distillation and po…
Inequity aversion improves cooperation in intertemporal social dilemmas
Edward Hughes, Joel Z. Leibo, Matthew G. Phillips +9
Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas. Models based on behavioral economics are only able to ex…
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
Joel Z. Leibo, Cyprien de Masson d'Autume, Daniel Zoran +10
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016). Psychlab enables implementations of classical laboratory…