Research map / Reinforcement learning / MDPs and planning
Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning
Sheng Zhang, Zhe Zhang, Siva Theja Maguluri
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 |
|---|---|---|---|
| vary lambda in {0, 0.2, 0.4, 0.8} for TD(lambda) with diminishing step sizes (ablation) | Average-reward TD(lambda) with linear function approximation · Random MRP, 100 states, 20 features | sample complexity / error decay | Mixed |
| start the algorithm from 4 different initial theta_0 | Average-reward TD(lambda) · Random MRP, 100 states, 20 features | E||Pi_{2,E}(theta_t - theta*)||_2 | No clear effect |
| start the algorithm from 4 different initial theta_0 | Average-reward TD(lambda) · Random MRP, 100 states, 20 features | component of (theta_t - theta*) along theta_e | Mixed |
| use diminishing step sizes beta_t = c1/(t+c2) instead of a constant step size | Average-reward TD(lambda) · Theorem 1 | mean-square distance to TD fixed set | Improved |
| add an intermediate lambda rather than very small or very large | Average-reward TD(lambda) sample complexity bound · Corollary 1 | sample complexity | Improved |
Closest papers by meaning
- Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 2024 · similarity 0.89)
- A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation (NeurIPS 2025 · similarity 0.89)
- Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs (NeurIPS 2024 · similarity 0.89)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 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.
