Research map / Reinforcement learning / Policy gradient and actor-critic
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces
Motoya Ohnishi, Masahiro Yukawa, Mikael Johansson, Masashi Sugiyama
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 continuous-time value-function approximation instead of discrete-time approximation with time interval 1.0 | MountainCarContinuous-v0 policy evaluation · MountainCarContinuous-v0 | cumulative cost: 299.1 -> 114.2; 299.1 -> 82.2 | Improved |
| Use continuous-time value-function approximation instead of discrete-time approximation with time interval 20.0 | MountainCarContinuous-v0 policy evaluation · MountainCarContinuous-v0 | cumulative cost: 89.2 -> 82.2; 90.4 -> 82.2 | Improved |
| Use a barrier-certified policy update | MountainCarContinuous-v0 policies · MountainCarContinuous-v0 | velocity violations: 10 -> 0; 20 -> 0 | Improved |
| Use CTGP instead of GPTD for policy improvement | Inverted pendulum · Inverted pendulum | time upright | Improved |
| Use continuous-time rather than discrete-time value-function approximation at small time intervals | MountainCarContinuous-v0 policy evaluation · MountainCarContinuous-v0 | sensitivity to time interval | Improved |
Closest papers by meaning
- Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations (NeurIPS 2020 · similarity 0.89)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.88)
- Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm (NeurIPS 2024 · similarity 0.88)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.88)
- A Temporal Difference Method for Stochastic Continuous Dynamics (NeurIPS 2025 · similarity 0.87)
- Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control (NeurIPS 2025 · 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.
