Research map / Reinforcement learning / Policy gradient and actor-critic
A Local Temporal Difference Code for Distributional Reinforcement 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 Laplace code (local TD ensemble over reward threshold, discount) instead of Expectile code after the task horizon shortens | Laplace code · Two-reward Markov process horizon change T to T' | quadratic error of estimates | Helped |
| decode Laplace code units with an expectile decoder (wrong assumption) instead of a Laplace decoder (ablation) | Laplace code with adaptive tuning · Dabney et al. variable-magnitude reward task | decoded reward distribution quality | No clear effect |
Closest papers by meaning
- Temporal-Difference Learning Using Distributed Error Signals (NeurIPS 2024 · similarity 0.88)
- Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Foundations of Multivariate Distributional Reinforcement Learning (NeurIPS 2024 · similarity 0.85)
- Reasoning with Latent Diffusion in Offline Reinforcement Learning (ICLR 2024 · similarity 0.85)
- STARC: A General Framework For Quantifying Differences Between Reward Functions (ICLR 2024 · similarity 0.85)
- Discerning Temporal Difference Learning (AAAI 2024 · similarity 0.85)
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.