Research map / Reinforcement learning / Policy gradient and actor-critic
Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
Semih Cayci, Atilla Eryilmaz
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 |
|---|---|---|---|
| add dynamic gradient clipping (Robust TD) to TD learning | projected TD learning with linear function approximation · randomly generated MRP, 256 states, Pareto tail index 1.2 | mean squared error | Improved |
| add dynamic gradient clipping (Robust TD) to TD learning | projected TD learning with linear function approximation · random MRP, 64 states, Pareto tail index 1.4 | mean squared error | Improved |
| add dynamic gradient clipping (Robust TD) to TD learning | projected TD learning · circular random walk, 256 states | mean squared error | Improved |
Closest papers by meaning
- Towards Parameter-Free Temporal Difference Learning (ICML 2026 · similarity 0.89)
- Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features (NeurIPS 2026 · similarity 0.88)
- Discerning Temporal Difference Learning (AAAI 2024 · similarity 0.87)
- Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification (NeurIPS 2024 · similarity 0.87)
- Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption (AAAI 2024 · similarity 0.86)
- Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization (ICML 2025 · 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.
