MARS-DA uses a top-level meta-controller to blend safe day-ahead allocation and real-time arbitrage sub-policies, delivering better risk-adjusted returns than baselines in a PJM-grounded two-settlement market simulator.
Grid2op-a testbed plat- form to model sequential decision making in power sys- tems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MARS-DA: A Hierarchical Reinforcement Learning Framework for Risk-Aware Multi-Agent Bidding in Power Grids
MARS-DA uses a top-level meta-controller to blend safe day-ahead allocation and real-time arbitrage sub-policies, delivering better risk-adjusted returns than baselines in a PJM-grounded two-settlement market simulator.