Research map / Reinforcement learning / Policy gradient and actor-critic
Learning Temporal Point Processes via Reinforcement Learning
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 |
|---|---|---|---|
| train policy via RL with analytic RKHS reward instead of MLE (RMTPP, similar RNN with exponential output) | RNN point process · 8 synthetic and real datasets, empirical intensity | intensity fit (qualitative) | Helped |
| RLPP vs adversarial WGANTPP training | RLPP · synthetic and real datasets, empirical intensity | intensity fit (qualitative) | No clear effect |
| RLPP vs parametric models under model misspecification | RLPP · synthetic and real datasets | intensity fit (qualitative) | Helped |
| use single-LSTM policy with analytic reward instead of generator plus discriminator LSTMs | RLPP vs WGANTPP · runtime averaged over datasets | training time: 1560m -> 80m | Helped |
| RLPP vs RMTPP training time | RLPP · runtime averaged over datasets | training time: 60m -> 80m | Hurt |
| RLPP vs LGCP | RLPP · 911 and MIMIC empirical intensity | intensity fit (qualitative) | No clear effect |
| RLPP vs LGCP runtime | RLPP · 911 dataset 5% subset | training time (min): 127 mins -> 80 mins | Helped |
Closest papers by meaning
- Deep Reinforcement Learning of Marked Temporal Point Processes (NeurIPS 2018 · similarity 0.90)
- Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes (AAAI 2023 · similarity 0.87)
- ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling (NeurIPS 2026 · similarity 0.86)
- The surprising efficiency of temporal difference learning for rare event prediction (NeurIPS 2024 · similarity 0.86)
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models (NeurIPS 2025 · similarity 0.86)
- A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning (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.