A bi-level actor-critic framework optimizes static spectral risk measures in online and offline RL, with tabular convergence guarantees and experiments on trading, portfolio, HIV, and MuJoCo tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning
A bi-level actor-critic framework optimizes static spectral risk measures in online and offline RL, with tabular convergence guarantees and experiments on trading, portfolio, HIV, and MuJoCo tasks.