DeepAI AI Chat
Log In Sign Up

BAM: Bayes with Adaptive Memory

by   Josue Nassar, et al.
NYU college
Stony Brook University
University of Washington

Online learning via Bayes' theorem allows new data to be continuously integrated into an agent's current beliefs. However, a naive application of Bayesian methods in non stationary environments leads to slow adaptation and results in state estimates that may converge confidently to the wrong parameter value. A common solution when learning in changing environments is to discard/downweight past data; however, this simple mechanism of "forgetting" fails to account for the fact that many real-world environments involve revisiting similar states. We propose a new framework, Bayes with Adaptive Memory (BAM), that takes advantage of past experience by allowing the agent to choose which past observations to remember and which to forget. We demonstrate that BAM generalizes many popular Bayesian update rules for non-stationary environments. Through a variety of experiments, we demonstrate the ability of BAM to continuously adapt in an ever-changing world.


page 1

page 2

page 3

page 4


Learning Fast and Slow for Online Time Series Forecasting

The fast adaptation capability of deep neural networks in non-stationary...

Taming Non-stationary Bandits: A Bayesian Approach

We consider the multi armed bandit problem in non-stationary environment...

Adaptive Sparse Gaussian Process

Adaptive learning is necessary for non-stationary environments where the...

Reset-Free Lifelong Learning with Skill-Space Planning

The objective of lifelong reinforcement learning (RL) is to optimize age...

An Approximate Bayesian Approach to Surprise-Based Learning

Surprise-based learning allows agents to adapt quickly in non-stationary...

HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory

Building Reinforcement Learning (RL) algorithms which are able to adapt ...

Lévy walks derived from a Bayesian decision-making model in non-stationary environments

Lévy walks are found in the migratory behaviour patterns of various orga...