Research map / Reinforcement learning / Policy gradient and actor-critic
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration
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 |
|---|---|---|---|
| MBS-QI zeta-filtration instead of vanilla FQI / behavior cloning | FQI on discretized CartPole · CartPole-v0 batch RL (epsilon 0.1-0.9) | policy value | Helped |
| filter on state-action support mu(s,a) (MBS-QI) instead of mu(a|s) thresholds (BCQL) or SPIBB | tabular Q iteration · CartPole-v0 batch RL | policy value | Helped |
| add state-support filter zeta(s) from VAE ELBO to BCQ | BCQ · Hopper-v3 imperfect batch | return | Helped |
Closest papers by meaning
- Continuous Doubly Constrained Batch Reinforcement Learning (NeurIPS 2021 · similarity 0.94)
- Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL (ICML 2021 · similarity 0.91)
- Batch Value-function Approximation with Only Realizability (ICML 2021 · similarity 0.91)
- Information-Theoretic Considerations in Batch Reinforcement Learning (ICML 2019 · similarity 0.90)
- Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity (ICLR 2024 · similarity 0.90)
- Information-Directed Pessimism for Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
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.