quote
active
quote:any-goal-or-purpose-can-be-well-thought-of-as-maximization-of-the-expected-value-of-the-cumulative-sum-of-a-received-scalar-signal-reward"any goal or purpose can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)"
The reward hypothesis underpinning RL, quoted from Sutton and Barto.
Source paper
extracted_from(2021) · Noor Sajid · Philip J. Ball · Thomas Parr · Karl J. Friston
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Concise statement of the free-energy principle's unification of action and perception.
- §3, preference learning discussion.
- Primary performance metric: total food visits across agent lifetime
- Foundational claim unifying action and perception within single optimization framework.
- Reinterprets classical reward/value concepts through free energy lens.
- Central thesis of the paper unifying cognitive phenomena under one objective function
- Deontological nature of predictive loss.
- Prediction orthogonality thesis.