Softmax Policy Prior

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

• Softmax policy selectionmethod0.845
  Selecting policies using a softmax (normalized exponential) function of negative expected free energy.
• The approximate posterior over policies is a softmax function of the negative expected free energy.claim0.763
  Mathematical form of policy selection, eq. (10).
• Softmax Inc.institute0.757
  Organisation that hosted the Holistic Intelligence unconference where the paper's ideas originated
• Softmax Bottleneckconcept0.742
  Failure mode for output-surjectivity: LLMs may lack capacity to predict all tokens due to rank constraints
• Softmax Functionmethod0.740
  Neuronal dynamics computed from free energy gradients; interpreted as average firing rate of neural populations.
• Prior Preferencesconcept0.726
  Target distribution over states or outcomes encoded in the generative model; goal states.
• Adaptive Beta Softmax Scalingmethod0.724
  Implementation detail weighting softmax by log(n_memories) to prevent down-weighting of attention values as memory set grows.
• Proximal Policy Optimizationmethod0.722
  RL algorithm used for training models to comply with the conflicting objective