scholarly journals Affine processes with compact state space

2018 ◽  
Vol 23 (0) ◽  
Author(s):  
Paul Krühner ◽  
Martin Larsson
Keyword(s):  
State Space ◽  
Affine Processes ◽  
Compact State

scholarly journals Generalized Representation Learning Methods for Deep Reinforcement Learning

2020 ◽  
Author(s):  
Hanhua Zhu
Keyword(s):  
Reinforcement Learning ◽  
State Space ◽  
Representation Learning ◽  
Learning Methods ◽  
New Methods ◽  
Compact State

Deep reinforcement learning (DRL) increases the successful applications of reinforcement learning (RL) techniques but also brings challenges such as low sample efficiency. In this work, I propose generalized representation learning methods to obtain compact state space suitable for RL from a raw observation state. I expect my new methods will increase sample efficiency of RL by understandable representations of state and therefore improve the performance of RL.

scholarly journals Renewal theory for functionals of a Markov chain with compact state space

2003 ◽  
Vol 31 (4) ◽  
pp. 2270-2300 ◽  
Author(s):  
Serguei Pergamenchtchikov ◽  
Claudia Kl�ppelberg
Keyword(s):  
Markov Chain ◽  
State Space ◽  
Renewal Theory ◽  
Compact State

scholarly journals Stability of non-linear filter for deterministic dynamics

2021 ◽  
Vol 0 (0) ◽  
pp. 0
Author(s):  
Anugu Sumith Reddy ◽  
Amit Apte
Keyword(s):  
State Space ◽  
Stochastic Dynamics ◽  
Initial Conditions ◽  
Linear Filter ◽  
Independent Observation ◽  
Deterministic Dynamics ◽  
Observation Process ◽  
Compact State ◽  
The Stability ◽  
Non Linear Filter

<p style='text-indent:20px;'>This papers shows that nonlinear filter in the case of deterministic dynamics is stable with respect to the initial conditions under the conditions that observations are sufficiently rich, both in the context of continuous and discrete time filters. Earlier works on the stability of the nonlinear filters are in the context of stochastic dynamics and assume conditions like compact state space or time independent observation model, whereas we prove filter stability for deterministic dynamics with more general assumptions on the state space and observation process. We give several examples of systems that satisfy these assumptions. We also show that the asymptotic structure of the filtering distribution is related to the dynamical properties of the signal.</p>

Diagnosability Analysis of Discrete Event Systems Using a Compact State Space Representation

2021 ◽  
Author(s):  
Xiaoting Zhang ◽  
Jiafeng Zhang ◽  
Zhong Zheng ◽  
Hanyu Zheng ◽  
Minglong Pu ◽  
...  
Keyword(s):  
State Space ◽  
Discrete Event Systems ◽  
Discrete Event ◽  
Space Representation ◽  
State Space Representation ◽  
Event Systems ◽  
Compact State
Sign in / Sign up

Export Citation Format

Share Document