Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming.
Supriyo GhoshLaura WynterShiau Hong LimDuc Thien NguyenPublished in: CoRR (2022)
Keyphrases
- stochastic programming
- reinforcement learning
- multistage
- chance constrained
- linear program
- decision making under uncertainty
- asset liability management
- network architecture
- risk averse
- fitted q iteration
- markov decision processes
- robust optimization
- power generation
- state space
- mathematical programming
- integer program