Research map / Learning theory and algorithms / Combinatorial and search optimization
Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients
Jongmin Lee, Wonseok Jeon, Geon-Hyeong Kim, Kee-Eung Kim
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 |
|---|---|---|---|
| add value-gradient ascent fine-tuning of action particles to UCT (ablation) | UCT with progressive widening · Pendulum, Acrobot, Reacher, Pusher (stochastic) | cumulative reward | Improved |
| add value-gradient ascent to KR-UCT (ablation) | KR-UCT · continuous control benchmarks | cumulative reward | Improved |
| add kernel regression information sharing (KR-UCT) to UCT | UCT · continuous control benchmarks | cumulative reward | No clear effect |
| use VG-UCT instead of UCT as policy improvement operator for policy network | MCTS-guided policy learning · four control tasks | cumulative reward | Improved |
| combine UCT global search with gradient ascent vs gradient-only (Grad-MPC) from random actions | Grad-MPC · 2D illustrative example | reaching goal | Improved |
| central difference instead of forward difference for value gradient (ablation) | VG-UCT · footnote | cumulative reward | No clear effect |
Closest papers by meaning
- Threshold UCT: Cost-Constrained Monte Carlo Tree Search with Pareto Curves (AAAI 2025 · similarity 0.89)
- Monte Carlo Tree Search in the Presence of Transition Uncertainty (AAAI 2024 · similarity 0.88)
- Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization (ICML 2024 · similarity 0.88)
- Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation (NeurIPS 2026 · similarity 0.88)
- Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search (ICML 2025 · similarity 0.88)
- Compositional Monte Carlo Tree Diffusion for Extendable Planning (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.
