Ground-Truth-First Benchmarking of Reinforcement Learning via Converse Optimality: From Smooth, Fully Observed Systems to Non-Smooth or Partially Observed Tasks
A ground-truth-first framework based on converse optimality is developed, constructing each task with a certified optimal value function and policy withheld from learners and used only for evaluation, and extends beyond smooth affine Gaussian systems to include non-affine raw-action interfaces and finite-covariance non...
Grégoire Ouerdane, Sinan Ibrahim, S. Streif et al.
· 0 citations