Research map / Reinforcement learning / Policy gradient and actor-critic
Semi-Parametric Efficient Policy Learning with Continuous Actions
Victor Chernozhukov, Mert Demirer, Greg Lewis, Vasilis Syrgkanis
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 the doubly robust estimator instead of the direct estimator | Personalized pricing policy evaluation · Synthetic pricing data, low-dimensional regime | policy-value estimation performance | Improved |
| Use the doubly robust estimator instead of the inverse propensity score estimator | Personalized pricing policy evaluation · Synthetic pricing data, low-dimensional regime | policy-value estimation performance | Improved |
| Use the doubly robust estimator instead of the oracle orthogonal estimator | Personalized pricing policy evaluation · Synthetic pricing data, low-dimensional regime | policy-value estimation performance | No clear effect |
| Use the doubly robust estimator instead of direct or inverse propensity score estimation | Personalized pricing policy optimization · Synthetic pricing data, four demand functions and constant or linear policies | regret | Improved |
| Use the doubly robust estimator instead of the direct model | Quadratic personalized pricing · Synthetic revenue model | policy-value estimation performance | Improved |
| Use the doubly robust estimator instead of the direct method | Costly resource allocation · Synthetic allocation data, low- and high-dimensional regimes | regret | Improved |
| Use the doubly robust estimator instead of the oracle method | Costly resource allocation · Synthetic allocation data, low- and high-dimensional regimes | regret | No clear effect |
Closest papers by meaning
- Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies (NeurIPS 2020 · similarity 0.90)
- A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes (ICML 2022 · similarity 0.89)
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (ICML 2016 · similarity 0.89)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.88)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.88)
- Off-policy estimation with adaptively collected data: the power of online learning (NeurIPS 2024 · similarity 0.88)
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.
