Timezone: »

Operator Splitting Value Iteration
Amin Rakhsha · Andrew Wang · Mohammad Ghavamzadeh · Amir-massoud Farahmand

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #724

We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function. Inspired by the splitting approach in numerical linear algebra, we introduce \emph{Operator Splitting Value Iteration} (OS-VI) for both Policy Evaluation and Control problems. OS-VI achieves a much faster convergence rate when the model is accurate enough. We also introduce a sample-based version of the algorithm called OS-Dyna. Unlike the traditional Dyna architecture, OS-Dyna still converges to the correct value function in presence of model approximation error.

Author Information

Amin Rakhsha (University of Toronto)
Andrew Wang (University of Toronto)
Mohammad Ghavamzadeh (Google Research)
Amir-massoud Farahmand (Vector Institute and University of Toronto)

More from the Same Authors