Research map / Reinforcement learning / Policy gradient and actor-critic
Dual Control for Approximate Bayesian Reinforcement Learning
Edgar D. Klenske, Philipp Hennig
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 |
|---|---|---|---|
| use approximate dual control instead of certainty equivalent control | CE controller · Dual control simulation, experiment column 1 | mean cost: 0.84 -> 0.77 | Improved |
| use approximate dual control instead of certainty equivalent control | CE controller · Dual control simulation, experiment column 2 | mean cost: 2.49 -> 1.96 | Improved |
| use approximate dual control instead of certainty equivalent control | CE controller · Dual control simulation, experiment column 3 | mean cost: 15.72 -> 14.33 | Improved |
| use approximate dual control instead of certainty equivalent control | CE controller · Dual control simulation, experiment column 4 | mean cost: 1.76 -> 1.62 | Improved |
| use approximate dual control instead of explicit Bayesian exploration bonus | CE-BEB controller · Dual control simulation, experiment column 1 | mean cost: 0.99 -> 0.77 | Improved |
| use approximate dual control instead of explicit Bayesian exploration bonus | CE-BEB controller · Dual control simulation, experiment column 2 | mean cost: 2.64 -> 1.96 | Improved |
| use approximate dual control instead of explicit Bayesian exploration bonus | CE-BEB controller · Dual control simulation, experiment column 3 | mean cost: 20.88 -> 14.33 | Improved |
| use approximate dual control instead of explicit Bayesian exploration bonus | CE-BEB controller · Dual control simulation, experiment column 4 | mean cost: 84.91 -> 1.62 | Improved |
| use approximate dual control, compared with oracle that knows true parameters | Oracle lower bound · Dual control simulation, experiment column 3 | mean cost: 7.15 -> 14.33 | Hurt |
Closest papers by meaning
- Bayesian Exploration Networks (ICML 2024 · similarity 0.88)
- Reinforcement Learning in Continuous Time and Space: A Stochastic Control Approach (JMLR 2020 · similarity 0.88)
- A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance (JMLR 2026 · similarity 0.87)
- Switching Linear Dynamics for Variational Bayes Filtering (ICML 2019 · similarity 0.87)
- Augmented Bayesian Policy Search (ICLR 2024 · similarity 0.86)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 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.
