A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
We present Γ-nets, a method for generalizing value function estimation over timescale. By using the timescale as one of the estimator's inputs we can estimate value for arbitrary timescales. ... Our results show that Γ-nets can be effective for predicting arbitrary timescales, with only a small cost in accuracy as compared to learning estimators for fixed timescales. ... This paper focuses on generalizing value estimation over timescale. ...arXiv:1911.07794v5 fatcat:ghjehh7pgfcx3lkqvp653sivrm
In this paper we present Γ-nets, a method for generalizing value function estimation over timescale, allowing a given GVF to be trained and queried for arbitrary timescales so as to greatly increase the ... There are many reasons why value estimates at multiple timescales might be useful; recent work has shown that value estimates at different time scales can be the basis for creating more advanced discounting ... This paper focuses on generalizing value estimation over timescale. ...doi:10.1609/aaai.v34i04.6027 fatcat:7kf4fmodiben7iwh7ccqzu45cy
General value functions (GVFs) are one approach to representing such relationships. ... Next, we introduce Γ-nets, which enable a single GVF estimator to make predictions for any fixed timescale within the training bounds, improving the tractability of learning and representing vast numbers ... We introduce a novel method, Γ-nets (Gamma-nets), which generalizes value estimation over timescale. ...doi:10.7939/r3-8bev-ap57 fatcat:yswep3oqm5fhpndxjpt52p6nom