Research map / Reinforcement learning / Policy gradient and actor-critic
Nonlinear Distributional Gradient 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 distributional GTD2 instead of regular GTD2 | Policy evaluation with control on Cartpole v0 and v1 · Cartpole v0 and Cartpole v1 | cumulative reward | Helped |
| Use distributional TDC instead of regular TDC | Policy evaluation with control on Cartpole v0 and v1 · Cartpole v0 and Cartpole v1 | cumulative reward | Helped |
| Use distributional GTD2 instead of GTD2 | Off-policy evaluation · Grid world | MSPBE | No clear effect |
| Use distributional GTD2 instead of GTD2 | Off-policy evaluation · Grid world | MSPBE variance | Helped |
| Use distributional Greedy-GQ instead of DQN | Control · Cartpole v0 | cumulative reward | Helped |
| Use distributional Greedy-GQ instead of C51 | Control · Cartpole v0 | cumulative reward | Helped |
| Use distributional Greedy-GQ instead of DQN | Control · LunarLander v2 | cumulative reward | Helped |
| Use distributional Greedy-GQ instead of DQN | Control · Vizdoom Defend the Center | cumulative reward | Helped |
| Use distributional Greedy-GQ instead of C51 | Control · Vizdoom Defend the Center | cumulative reward | Mixed |
Closest papers by meaning
- Statistical Efficiency of Distributional Temporal Difference Learning (NeurIPS 2024 · similarity 0.91)
- A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation (NeurIPS 2025 · similarity 0.91)
- Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model (NeurIPS 2024 · similarity 0.88)
- Foundations of Multivariate Distributional Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features (NeurIPS 2026 · similarity 0.87)
- Revisiting a Design Choice in Gradient Temporal Difference Learning (ICLR 2025 · similarity 0.87)
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.