Research map / Reinforcement learning / MDPs and planning
Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards
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 |
|---|---|---|---|
| Use model-based UCB-style reinforcement learning with PAMM parameter estimates and offline planning | Incrementality bidding · Online episodes | regret: O(H^2 \sqrt{\log(HT/\delta) T} + H^2 \log(T/\delta)) | Helped |
| Match conversion-count moments across episodes with the same prior winning history | PAMM incrementality parameter estimation · Incrementality parameter estimation | absolute estimation error: C_1 \sqrt{\frac{\log{1/\delta}}{n_h}}; C_2 \sqrt{\frac{\log{1/\delta}}{n_{h}(\ell)}} | Helped |
| Use an optimism confidence region for incrementality parameters | Online Bidding algorithm · Incrementality bidding, online episodes | regret: O(H^2 \sqrt{\log(HT/\delta) T} + H^2 \log(T/\delta)) | Helped |
Closest papers by meaning
- Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards (NeurIPS 2025 · similarity 0.89)
- Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback (NeurIPS 2022 · similarity 0.87)
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback (NeurIPS 2025 · similarity 0.85)
- Online Markov Decision Processes Configuration with Continuous Decision Space (AAAI 2024 · similarity 0.85)
- Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints (ICML 2024 · similarity 0.85)
- Online Episodic Convex Reinforcement Learning (ICML 2025 · similarity 0.85)
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.