Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Logo of CS4People
Events

The Taub Faculty of Computer Science Events and Talks

ContraBAR: Contrastive Bayes-Adaptive Deep RL
event speaker icon
Era Choshen (M.Sc. Thesis Seminar)
event date icon
Thursday, 16.03.2023, 11:00
event location icon
Taub 601
event speaker icon
Advisor: Prof. Aviv Tamar
In meta reinforcement learning (meta RL), an agent seeks a Bayes-optimal policy – the optimal policy when facing an unknown task that is sampled from some known task distribution. Previous approaches tackled this problem by inferring a belief over task parameters, using variational inference methods. Motivated by recent successes of contrastive learning approaches in RL, such as contrastive predictive coding (CPC), we investigate whether contrastive methods can be used for learning Bayes-optimal behavior. We begin by proving that representations learned by CPC are indeed sufficient for Bayes optimality. Based on this observation, we propose a simple meta RL algorithm that uses CPC in lieu of variational belief inference. Our method, ContraBAR, achieves comparable performance to state-of-the-art in domains with state-based observation and circumvents the computational toll of future observation reconstruction, enabling learning in domains with image-based observations. It can also be combined with image augmentations for domain randomization and used seamlessly in both online and offline meta RL settings.