Multi-Agent Deep Deterministic Policy Gradient (MADDPG)

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

• Multiple Gradient Descent Algorithm (MGDA)method0.758
  Gradient balancing by solving multi-objective optimization for minimum-norm aggregated gradient.
• dynamic expectation maximisation (DEM)method0.713
  A variational approach for dynamic Bayesian inversion of nonlinear causal models, named in this paper.
• Gradient-based data attributionmethod0.704
  Baseline method against which probe-based ranking is compared; more computationally expensive.
• maximum-norm gradient normalizationmethod0.702
  Training-free technique normalizing all task gradients to the maximum gradient norm magnitude
• Markov Decision Process (MDP)framework0.700
  Generative model substrate for active inference; discrete states, actions, outcomes, and temporal policies.
• Gradient Descentmethod0.698
  Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data
• Mean Difference Vector Patching (MDVP)method0.696
  Intervention method adding the difference in mean activations between two conditions to a representation
• Partially Observable Markov Decision Process (POMDP)framework0.693
  Modeling framework for discrete state-space decision-making under uncertainty, used as generative model in active inference.