Research map / Reinforcement learning / Policy gradient and actor-critic
Off-Policy Evaluation via Off-Policy Classification
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 OPC instead of the strongest reported baseline metric | Off-policy policy evaluation · Binary tree and Pong | Correlation with true return: Tree: R^2 0.00 -> 0.21; Pong: R^2 0.09 -> 0.50 | Helped |
| Use OPC instead of the strongest reported baseline metric | Off-policy policy evaluation · Sim Train | Correlation with true return: R^2 0.74 -> 0.49; Spearman ξ 0.81 -> 0.86 | Mixed |
| Use OPC instead of the strongest reported baseline metric | Off-policy policy evaluation · Sim Test | Spearman ξ: 0.78 -> 0.66 | Hurt |
| Use SoftOPC instead of the strongest reported baseline metric | Off-policy policy evaluation · Sim Test | Spearman ξ: 0.78 -> 0.77 | No clear effect |
| Use SoftOPC instead of the strongest reported baseline metric | Off-policy policy evaluation · Real-world grasping | Spearman ξ: 0.50 -> 0.94 | Helped |
| Replace the soft loss with the thresholded 0-1 loss | OPC / SoftOPC · Pong models trained with γ=0.9 | Model separation | Helped |
Closest papers by meaning
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.94)
- Efficient Off-Policy Learning for High-Dimensional Action Spaces (ICLR 2025 · similarity 0.91)
- Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning (NeurIPS 2017 · similarity 0.91)
- More Efficient Off-Policy Evaluation through Regularized Targeted Learning (ICML 2019 · similarity 0.91)
- Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies (ICLR 2024 · similarity 0.90)
- Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic (ICML 2024 · similarity 0.90)
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.