2 papers
cs.LG2025
Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent
Gabriel Nixon Raj
We study sequential decision-making under distribution drift. We propose entropy-regularized trust-decay, which injects stress-aware exponential tilting into both belief updates an…
q-fin.PM2025
Adaptive and Regime-Aware RL for Portfolio Optimization
Gabriel Nixon Raj
This study proposes a regime-aware reinforcement learning framework for long-horizon portfolio optimization. Moving beyond traditional feedforward and GARCH-based models, we design…