Combining absolute, relative, and forecast price features in the state for Double DQN agents improves arbitrage performance and cross-zone transfer in pumped-storage hydro trading compared to single feature families.
State representation learning for control: An overview , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.
citing papers explorer
-
State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Combining absolute, relative, and forecast price features in the state for Double DQN agents improves arbitrage performance and cross-zone transfer in pumped-storage hydro trading compared to single feature families.
-
Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.