Pedro Ortega — accepted AI-conference papers

2021

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega +7

ICML 2021spotlight

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar{é} recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then inves…

Cited by 105 Source ↗PDF ↗Scholar ↗

2020

Meta-trained agents implement Bayes-optimal agents

Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg +1

NeurIPS 2020spotlight

Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol incentivises agents to behave Bayes-optimally. We empirically in…

Cited by 49 Source ↗PDF ↗Scholar ↗

2019

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning

Natasha Jaques, Angeliki Lazaridou, Edward Hughes, Caglar Gulcehre, Pedro Ortega, Dj Strouse +2

ICML 2019oral

We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents’ actions. Causal influence is assessed using counterfactual reasoning. At each timestep, an agent simulates…

Cited by 603 Source ↗PDF ↗code ↗Scholar ↗

2015

Reactive bandits with attitude

Pedro Ortega, Kee-Eung Kim, Daniel Lee

AISTATS 2015poster

We consider a general class of K-armed bandits that adapt to the actions of the player. A single continuous parameter characterizes the “attitude” of the bandit, ranging from stochastic to cooperative or to fully adversarial in nature. The player seeks to maximize the expected return from the adapti…

Cited by 2 Source ↗PDF ↗Scholar ↗