Research map / Optimization / Nonconvex and smooth optimization
Provably Efficient Neural GTD for Off-Policy Learning
Hoi-To Wai, Zhuoran Yang, Zhaoran Wang, Mingyi Hong
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 |
|---|---|---|---|
| replace neural TD with neural GTD (primal-dual min-max) for off-policy learning | 2-layer ReLU NN · Garnet MDP, |S|=500, |A|=5, gamma=0.9 | average MSBE vs. width m | Improved |
| neural TD under off-policy data as width m increases | neural TD · Garnet MDP, |S|=500, |A|=5, gamma=0.9 | average MSBE vs. width m | No clear effect |
| increase number of neurons m | neural GTD · Garnet MDP off-policy | average MSBE | Improved |
Closest papers by meaning
- A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning (JMLR 2022 · similarity 0.87)
- An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning (JMLR 2016 · similarity 0.87)
- Revisiting a Design Choice in Gradient Temporal Difference Learning (ICLR 2025 · similarity 0.85)
- An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks (ICML 2024 · similarity 0.84)
- On Double Descent in Reinforcement Learning with LSTD and Random Features (ICLR 2024 · similarity 0.84)
- Neural Network Approximation for Pessimistic Offline Reinforcement Learning (AAAI 2024 · similarity 0.84)
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.
