Skip to content
#

temporal-difference-learning

Here are 43 public repositories matching this topic...

AppliedGameTheoryHomeworkSolutions

Deep reinforcement learning with sparse terminal-only rewards: error-defined neural Q-learning inspired by random network distillation (RND). PyTorch code and reproducible LunarLander-v3 experiments; one monitor-selected checkpoint achieved 84.4% landings over 500 held-out episodes.

  • Updated Nov 14, 2026
  • Python

Add this topic to your repo

To associate your repository with the temporal-difference-learning topic, visit your repo's landing page and select "manage topics."

Learn more

⌂ 换网址