arXiv CS
open access
Closing the Horizon Gap in Policy Optimization for Adversarial MDPs
We consider policy optimization for online episodic tabular Markov decision processes (MDPs) with adversarial losses and bandit feedback. Policy optimization updates the policy locally at each state and avoids optimization over the occupancy-measure polytope, but its existing regret bounds are large
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Closing the Horizon Gap in Policy Optimization for Adversarial MDPs#1249786
- Provably Optimal Reinforcement Learning under Safety Filtering#1034680
- Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning#999991
- Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback#1202387
- Stochastic Optimization Algorithms for Problems with Controllable Biased Oracles#1123900
Record · ID 1242744
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive