Searcharxiv⌕ Search

arXiv subjects

Ercan Atam

Publications and source records attributed to Ercan Atam.

2 recordsLinked to original sources

Internalizing Investment Mandates: A Neurosymbolic RL Approach to Portfolio Allocation

Institutional portfolios operate under investment policy statements that specify asset allocation constraints, often conditioned on market regime information. Deep reinforcement learning has been shown to optimize financial performance but typically does not enforce rule compliance, making it unsuitable for real-world deployment. Existing neurosymbolic methods such as Probabilistic Logic Policy Gradient (PLPG) offer constraint-satisfying reinforcement learning (RL) via differentiable symbolic supervision but assume a finite, discrete action space. We present a PLPG-inspired continuous allocation method that estimates the probability that the policy's own executed action satisfies the investment mandate, using reparameterized Monte Carlo sampling, and adds it to the training objective. No post-hoc enforcement mechanism intercepts actions at inference time and compliance is learned by the agent. Audited directly on deterministic mean actions with no correction, the policy reduces violations of a six-rule regime-conditional mandate from 96-98% for unconstrained RL and 33.4% for a reward-penalty baseline to 4.8%, showing that a continuous-action neurosymbolic policy can substantially internalize a symbolic mandate.

cs.LG↗

A hybrid green energy-based framework with a multi-objective optimization approach for optimal frost prevention in horticulture

In this paper, first we propose a novel hybrid renewable energy-based solution for frost prevention in horticulture applications involving active heaters. Then, we develop a multi-objective robust optimization-based formulation to optimize the distribution of a given number of active heaters in a given large-scale orchard. The objectives are to optimally heat the orchard by the proposed frost prevention system and to minimize the total length of the energy distribution pipe network (which is directly related to the installation cost and the cost of energy losses during energy transfer). Next, the resulting optimization problem is approximated using a discretization scheme. A case study is provided to give an idea of the potential savings using the proposed optimization method compared to the result from a heuristic-based design, which showed a 24.13% reduction in the total pipe length and a 54.29% increase in frost prevention.

eess.SY↗