method
active
method:reward-shapingReward Shaping
Subtract λ times concept score from reward.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Unifying framework: remove or amplify a concept's term in the exponential-tilt reward.
Methods (2)
method
- Replicates Lu et al. / Chen et al. contrastive-pair recipe.
- Apply shaping offset only on creative-writing subset C.
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.
- High-level signals that exploit agential nature of cells to achieve outcomes without micromanaging hardware; evolution searches this space.
- The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
- Central question: does geometry in activation space causally determine behavior?
- Pragmatic or extrinsic value component of expected free energy; preference maximization.
- Reinterpretation of rewards as simply predictable (unsurprising) stimuli under the free-energy principle.
- Rewards correlate with unintended features.
- Quirky RM biases forming the hidden goal of the studied model.