Observational Overfitting in Reinforcement Learning

Xingyou Song

[0]

Yiding Jiang

Yilun Du

[0]

Behnam Neyshabur

[0]

international conference on learning representations, 2020.

Cited by: 0|Views31

Keywords:

observational overfitting reinforcement learning generalizationMore(3+)

Weibo:

We have identified and isolated a key component of overfitting in reinforcement learning as the particular case of “observational overfitting”, which is attractive for studying architectural implicit regularizations

Abstract:

A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP). We provide a general framework for analyzing this scenario, which we use to design multiple synthe...More

Code:

Data:

Full Text

View via Publisher