Research map / Reinforcement learning / Policy gradient and actor-critic
CoinDICE: Off-Policy Confidence Interval Estimation
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 CoinDICE instead of concentration-based confidence interval estimators | Two-armed bandit · Two-armed bandit | interval coverage | Helped |
| Use CoinDICE instead of Student's t-test or bootstrap intervals | Two-armed bandit · Two-armed bandit | interval log-width | Helped |
| Use CoinDICE instead of baseline confidence interval estimators | FrozenLake and Taxi · FrozenLake and Taxi | interval coverage | Helped |
| Use CoinDICE instead of baseline confidence interval estimators | FrozenLake and Taxi · FrozenLake and Taxi | interval log-width | Helped |
| Use CoinDICE instead of importance-sampling-based methods | Reacher · Reacher | interval coverage | Helped |
| Optimize the CoinDICE Lagrangian in the neural-network setting | CoinDICE · Reacher | interval coverage | Hurt |
Closest papers by meaning
- DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections (NeurIPS 2019 · similarity 0.90)
- Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies (NeurIPS 2020 · similarity 0.89)
- Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design (ICML 2024 · similarity 0.88)
- Dynamic Uncertainty Estimation for Offline Reinforcement Learning (AAAI 2025 · similarity 0.88)
- SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning (AAAI 2025 · 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.