Reconciling λ-Returns with Experience Replay

Brett Daley, Christopher Amato

Oct-3-2025, 08:18:50 GMT–Neural Information Processing Systems

A unique benefit to this approach is that each transition's TD error can be

arxiv preprint arxiv, learning, reinforcement learning, (13 more...)

Neural Information Processing Systems

Oct-3-2025, 08:18:50 GMT

Conferences PDF

Country:
- North America
  - Canada (0.04)
  - United States > Massachusetts
    - Suffolk County > Boston (0.04)

Genre:
- Research Report (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models > Undirected Networks
      - Markov Models (0.46)
    - Neural Networks > Deep Learning (0.47)
    - Reinforcement Learning (1.00)
  - Representation & Reasoning (0.93)

Duplicate Docs Excel Report

Title
Reconciling λ-Returns with Experience Replay

Similar Docs Excel Report more

Title	Similarity	Source
None found