task · first seen 14 Oct 2026
policy identification
Determining a near-optimal policy from sampled experience and bounding the sample complexity required.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Average-Reward Policy Identification from a Single Continuing TrajectoryPapers · 14 Oct 2026 · Tongxi Wang
Latest sources
- Average-Reward Policy Identification from a Single Continuing TrajectoryPapers · 14 Oct 2026 · Tongxi Wang