Research map / Reinforcement learning / Visual and representation RL
Adaptive Model Design for Markov Decision Process
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 |
|---|---|---|---|
| Fixed regularization parameter epsilon set to a median value (vs. extreme values) in the tax design experiment (ablation) | Adaptive model design (tax design macroeconomic model) · Tax design macroeconomic model | discounted total social welfare / convergence rate | Helped |
| Very large epsilon (ϵ=50) in tax design (ablation) | Adaptive model design (tax design macroeconomic model) · Tax design macroeconomic model | discounted total social welfare | Hurt |
| Small epsilon (ϵ=1) in tax design (ablation) | Adaptive model design (tax design macroeconomic model) · Tax design macroeconomic model | design objective gap | Hurt |
| Epsilon-adaptive strategy (increasing epsilon step by step during training) (ablation) | Adaptive model design · Tax design macroeconomic model and two-ankle robotic arm | convergence speed to optimum | Helped |
| Small number of inner iterations K (K=1) instead of larger K (ablation) | Adaptive model design (tax design) · Tax design macroeconomic model | learning curve stability | Hurt |
| Adaptive design method vs. Bayesian Optimization (Mguni et al. 2019) when tuning consumption tax only | Adaptive model design · Tax design macroeconomic model | discounted total social welfare | No clear effect |
Closest papers by meaning
- How RL Agents Behave When Their Actions Are Modified (AAAI 2021 · similarity 0.88)
- Model-Based Exploration in Monitored Markov Decision Processes (ICML 2025 · similarity 0.87)
- Learn to change the world: Multi-level reinforcement learning with model-changing actions (ICML 2026 · similarity 0.87)
- Augmenting Markov Decision Processes with Advising (AAAI 2019 · similarity 0.87)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.86)
- When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL (NeurIPS 2024 · similarity 0.85)
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.