Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs

Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs

200 pages· 2009· ISBN 9781109244403
Join Readfeed freeFind clubs reading this bookBrowse readable books
About
The last part of this research program explores the computational merits obtained by heuristical implementations that result from the integration of the ONV problem developments into the PAC-algorithms developed in the first part of this work. We study, through numerical experimentation, the relative performance of these resulting heuristical implementations in comparison to (i) the initial version of the PAC-learning algorithms, presented in the first part of the research program, and (ii) standard Q-learning algorithm variations provided in the RL literature. The work presented in this last part reinforces and confirms the driving assumption of this research, i.e., that one can design customized RL algorithms of enhanced performance if the underlying problem structure is taken into account.

Discuss Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs with other readers

Join or start a book club for Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs on Readfeed. Live chat, shared reading progress, and AI discussion questions — free to get started.

Sign up freeBrowse book clubs

Frequently asked questions

How do I join a book club for Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs?

Sign up free on Readfeed, then browse public clubs or start your own club with Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs as the current read. Invite friends with a share link and discuss together with live chat and AI discussion questions.

Can I discuss Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs with other readers online?

Yes. Readfeed book clubs let you chat live, share progress, and join discussions about Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces, And, The Optimal Node Visitation Problem in Acyclic Stochastic Digraphs with readers worldwide — whether your club is virtual, in-person, or hybrid.

Is Readfeed free?

Yes. Creating an account and joining book clubs is free. Sign up to find readers who love the same books and start discussing today.