Research map / Bandits and online learning / RL theory and MDPs
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
Falcon Dai, Matthew Walter
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace the diameter-based value-span bound with the MEHC bound | UCRL2-style regret analysis · MDPs whose actual model lies in the extended MDP | optimal value span upper bound: r_\text{max} D(M) -> \kappa(M) | Improved |
| Use MEHC instead of diameter in the regret bound | UCRL2 · Average-reward MDPs | regret upper bound: 34 \max\{1, \kappa\} S \sqrt{AT \log\left(\frac{T}{\delta}\right)} | Improved |
| Apply potential-based reward shaping to make transition-relevant actions more distinguishable in the toy MDP | Two-state toy MDP · Two-state toy MDP | MEHC: \frac{\alpha + \beta}{2 \epsilon} < \frac{\alpha}{\epsilon} | Improved |
| Apply any bounded potential-based reward shaping transformation | MDP with finite MEHC and unsaturated optimal average reward · MDPs with finite MEHC and unsaturated optimal average reward | MEHC: \frac{1}{2} \kappa(M) \leq \kappa(M^\varphi) \leq 2 \kappa(M) | Mixed |
Closest papers by meaning
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.89)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (AAAI 2024 · similarity 0.88)
- Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes (ICLR 2025 · similarity 0.88)
- Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs (NeurIPS 2024 · similarity 0.88)
- Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach (NeurIPS 2025 · similarity 0.88)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
