ReincarnatingReinforcementLearning: ReusingPriorComputationtoAccelerateProgress

Feb-11-2026, 14:45:48 GMT–Neural Information Processing Systems

The vertical separators correspond to loading network weights and replay buffer for fine-tuning while offline pre-training on replay buffer using QDagger (Section 4.1) for reincarnation. Shaded regions show 95% confidence intervals.

artificial intelligence, machine learning, reinforcement learning, (16 more...)

Neural Information Processing Systems

Feb-11-2026, 14:45:48 GMT

Conferences PDF

Add feedback

Genre:
- Research Report
  - Experimental Study (0.34)
  - New Finding (0.34)

Industry:
- Education (0.68)
- Leisure & Entertainment > Games (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks (1.00)
    - Reinforcement Learning (1.00)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Similar Docs Excel Report more

Title	Similarity	Source
None found