Vertes, E; Sahani, M; (2019) A neurally plausible model learns successor representations in partially observable environments. In: Proceedings of 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). NIPS Proceedings: Vancouver, Canada.

Preview

Text neurally_plausible_model.pdf - Published Version Download (786kB) | Preview

Abstract

Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent's location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sensory information. Successor representations (SR) have been proposed as a middle-ground between model-based and model-free reinforcement learning strategies, allowing for fast value computation and rapid adaptation to changes in the reward function or goal locations. Indeed, recent studies suggest that features of neural responses are consistent with the SR framework. However, it is not clear how such representations might be learned and computed in partially observed, noisy environments. Here, we introduce a neurally plausible model using \emph{distributional successor features}, which builds on the distributed distributional code for the representation and computation of uncertainty, and which allows for efficient value function computation in partially observed environments via the successor representation. We show that distributional successor features can support reinforcement learning in noisy environments in which direct learning of successful policies is infeasible.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item