Research map / Learning theory and algorithms / Sample complexity
Markov Decision Processes with Time-Varying Geometric Discounting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Model time-varying discounting as a sequential game among time-indexed selves | Infinite-horizon MDPs · Discount functions converging to a limit outside Γ | exact SPE existence | Helped |
| Use a down-step discount function with binary-encoded T | SPE-Start · Down-step discount functions | computational complexity | Hurt |
| Relax exact equilibrium to ε-SPE | Infinite-horizon MDPs · Discount functions converging to any limit in [0,1] | ε-SPE existence | Helped |
| Approximate the discount-function tail by a constant and construct earlier policies by backward induction | ε-SPE computation · Discount functions that are (α,β)-convergent and have limit below 1 by a known constant | computation time | Helped |
Closest papers by meaning
- Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor (NeurIPS 2023 · similarity 0.89)
- Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time (NeurIPS 2023 · similarity 0.88)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.87)
- Anytime-Constrained Equilibria in Polynomial Time (ICML 2025 · similarity 0.86)
- On the Convergence of Single-Timescale Actor-Critic (NeurIPS 2025 · similarity 0.86)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.86)
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.