Research map / Reinforcement learning / Policy gradient and actor-critic
Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes
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 irregular event timing and endogenous jumps with NHPI, and plan using the SMDP Bellman equation | SEDRL · Synthetic simulation (SI and USI) | cumulative reward | Helped |
| Use NHPI-based model-based planning rather than the compared RL baselines | Smart broadcasting · Smart broadcasting | cumulative reward: -10; below -40 | Helped |
| Use NHPI-based model-based planning rather than the compared RL baselines | Improving the Engagement · Improving the Engagement | cumulative reward: -35; below -50 | Helped |
| Represent irregular event intervals explicitly with a temporal point process rather than treating timestamps as regular features | SEDRL · Synthetic simulation | cumulative reward | Helped |
| Use real replay-buffer data for value learning rather than fully imagined data (ablation) | SEDRL · Experiments | performance | Helped |
Closest papers by meaning
- A Temporal Difference Method for Stochastic Continuous Dynamics (NeurIPS 2025 · similarity 0.89)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.88)
- Reinforcement Learning with Random Time Horizons (ICML 2025 · similarity 0.86)
- Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics (ICLR 2025 · similarity 0.86)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.86)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · 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.