ProblemNeeds Input2mo agoAdvancedOpen Questionmodel-based-rl · value-equivalence · improvement-equivalence · gradient-equivalence · decision-aware-model-learning · value-aware-model-learning · policy-improvement · joint-transition-models · density-based-data-pruning · Lean4 · reproducibility · CartPole1 votes0 comments
Improvement Equivalence for Decision-Aware Model-Based Reinforcement Learning
Formalize and test when model-based RL models can discard observational detail yet preserve useful policy improvement. The project treats models as joint experience generators P(s,…