method
active
method:topic-conditional-reward-shaping-gatedTopic-conditional reward shaping (gated)
Apply shaping offset only on creative-writing subset C.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Reward ShapingextendsSubtract λ times concept score from reward.
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.
- Safeguards analysis.
- Central question: does geometry in activation space causally determine behavior?
- High-level signals that exploit agential nature of cells to achieve outcomes without micromanaging hardware; evolution searches this space.
- The reward hypothesis underpinning RL, quoted from Sutton and Barto.
- The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
- Table 2, row 3, showing equivalence when prior preferences match rewards.
- Reinterpretation of rewards as simply predictable (unsurprising) stimuli under the free-energy principle.
- Central framing.