Login / Signup

When Your AIs Deceive You: Challenges with Partial Observability of Human Evaluators in Reward Learning.

Leon LangDavis FooteStuart RussellAnca D. DraganErik JennerScott Emmons
Published in: CoRR (2024)
Keyphrases
  • reinforcement learning
  • partial observability
  • learning process
  • learning algorithm
  • learning tasks
  • machine learning
  • knowledge acquisition
  • neural network
  • multi agent
  • human experts
  • partially observable