"reinforcement learning is learning what to do – how to map situations to actions – so as to maximize a numerical reward signal"

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Reinforcement Learningframework0.857
  Alternative framework for agent behavior; based on reward maximization rather than free energy minimization.
• Reinforcement Learning from Human Feedbackmethod0.833
  Method for fine-tuning LMs based on human preferences; mentioned as combining RL and LMs.
• How Does Reinforcement Learning At The Level Ofquestion0.818
• Deep Reinforcement Learningmethod0.808
  AI training method inspired by behaviorism, used for autonomous cars and drones; cited as bioinspired success
• Reinforcement Learning from AI Feedbackframework0.807
  Variant of RLHF where human feedback is replaced with AI-generated feedback for harmlessness.
• Reinforcement learning (RL)concept0.807
  Machine learning paradigm where agents learn to maximize cumulative reward through interaction.
• Reinforcement learning can be regarded as a limiting or special case of model-based approaches in general — or active inference in particular — when epistemic value is removed.claim0.801
  §3 Discussion.
• Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.800
  Key insight linking individual rewards to system-level learning.