Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Šiška, David"'
We analyse the regret arising from learning the price sensitivity parameter $\kappa$ of liquidity takers in the ergodic version of the Avellaneda-Stoikov market making model. We show that a learning algorithm based on a regularised maximum-likelihood
Externí odkaz:
http://arxiv.org/abs/2409.02025
Entropy regularization has been extensively used in policy optimization algorithms to regularize the optimization landscape and accelerate convergence; however, it comes at the cost of introducing an additional regularization bias. This work quantifi
Externí odkaz:
http://arxiv.org/abs/2405.20250
This paper studies the convergence of the mirror descent algorithm for finite horizon stochastic control problems with measure-valued control processes. The control objective involves a convex regularisation function, denoted as $h$, with regularisat
Externí odkaz:
http://arxiv.org/abs/2401.01198
We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space. The flow is a continuous-time analogue of a policy mirror descent method. We e
Externí odkaz:
http://arxiv.org/abs/2310.02951
We investigate whether the fee income from trades on the CFM is sufficient for the liquidity providers to hedge away the exposure to market risk. We first analyse this problem through the lens of continuous-time financial mathematics and derive an up
Externí odkaz:
http://arxiv.org/abs/2302.04345
Autor:
Sethi, Deven, Šiška, David
The modified Method of Successive Approximations (MSA) is an iterative scheme for approximating solutions to stochastic control problems in continuous time based on Pontryagin Optimality Principle which, starting with an initial open loop control, so
Externí odkaz:
http://arxiv.org/abs/2212.05784
We produce uniform and decaying bounds in time for derivatives of the solution to the backwards Kolmogorov equation associated to a stochastic processes governed by a time dependent dynamics. These hold under assumptions over the integrability proper
Externí odkaz:
http://arxiv.org/abs/2207.12871
We study the global convergence of policy gradient for infinite-horizon, continuous state and action space, and entropy-regularized Markov decision processes (MDPs). We consider a softmax policy with (one-hidden layer) neural network approximation in
Externí odkaz:
http://arxiv.org/abs/2201.07296
Using a combination of recurrent neural networks and signature methods from the rough paths theory we design efficient algorithms for solving parametric families of path dependent partial differential equations (PPDEs) that arise in pricing and hedgi
Externí odkaz:
http://arxiv.org/abs/2011.10630
The classical Method of Successive Approximations (MSA) is an iterative method for solving stochastic control problems and is derived from Pontryagin's optimality principle. It is known that the MSA may fail to converge. Using careful estimates for t
Externí odkaz:
http://arxiv.org/abs/2007.05209