Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

06/29/2020
by   Jianzhun Du, et al.
0

We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Our models accurately characterize continuous-time dynamics and enable us to develop high-performing policies using a small amount of data. We also develop a model-based approach for optimizing time schedules to reduce interaction rates with the environment while maintaining the near-optimal performance, which is not possible for model-free methods. We experimentally demonstrate the efficacy of our methods across various continuous-time domains.

READ FULL TEXT
research
05/23/2022

Logarithmic regret bounds for continuous-time average-reward Markov decision processes

We consider reinforcement learning for continuous-time Markov decision p...
research
07/25/2018

Continuous-Time Markov Decisions based on Partial Exploration

We provide a framework for speeding up algorithms for time-bounded reach...
research
05/28/2018

Dual Policy Iteration

Recently, a novel class of Approximate Policy Iteration (API) algorithms...
research
03/16/2022

Multiscale Sensor Fusion and Continuous Control with Neural CDEs

Though robot learning is often formulated in terms of discrete-time Mark...
research
02/17/2020

The Probabilistic Model Checker Storm

We present the probabilistic model checker Storm. Storm supports the ana...
research
04/19/2023

Model Based Reinforcement Learning for Personalized Heparin Dosing

A key challenge in sequential decision making is optimizing systems safe...
research
07/25/2022

Meta Neural Ordinary Differential Equations For Adaptive Asynchronous Control

Model-based Reinforcement Learning and Control have demonstrated great p...

Please sign up or login with your details

Forgot password? Click here to reset