Research map / Reinforcement learning / Policy gradient and actor-critic
Target-Based Temporal-Difference Learning
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 averaging target updates (A-TD) instead of standard TD | Linear TD policy evaluation · 10-state MDP simulation | convergence error | Helped |
| Use averaging target updates (A-TD) instead of standard TD | Linear TD policy evaluation · 10-state MDP simulation, early iterations | convergence speed | Hurt |
| Use periodic target updates with the adaptive subproblem step size and L_k=40 instead of standard TD | Periodic TD (P-TD) · 10-state MDP simulation with three features | convergence error | Helped |
| Use the same step-size rule for every outer-loop subproblem rather than an adaptive rule (ablation) | Periodic TD (P-TD) · 10-state MDP simulation with three features | stability | Hurt |
Closest papers by meaning
- An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks (ICML 2024 · similarity 0.89)
- Discerning Temporal Difference Learning (AAAI 2024 · similarity 0.88)
- On Double Descent in Reinforcement Learning with LSTD and Random Features (ICLR 2024 · similarity 0.87)
- Simplifying Deep Temporal Difference Learning (ICLR 2025 · similarity 0.86)
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities (NeurIPS 2026 · similarity 0.86)
- Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features (NeurIPS 2026 · similarity 0.86)
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.