ActiveInference.action_select
— MethodSelects action from computed actions probabilities – used for stochastic action sampling
ActiveInference.array_of_any
— MethodCreates an array of "Any" with the desired number of sub-arrays
ActiveInference.array_of_any_uniform
— MethodCreates an array of "Any" as a uniform categorical distribution
ActiveInference.array_of_any_zeros
— MethodCreates an array of "Any" with the desired number of sub-arrays filled with zeros
ActiveInference.calc_expected_utility
— MethodCalculate Expected Utility
ActiveInference.calc_free_energy
— FunctionCalculate Free Energy
ActiveInference.calc_pA_info_gain
— MethodCalculate observation to state info Gain
ActiveInference.calc_pB_info_gain
— MethodCalculate state to state info Gain
ActiveInference.calc_states_info_gain
— MethodCalculate States Information Gain
ActiveInference.compute_accuracy
— MethodCalculate Accuracy Term
ActiveInference.compute_accuracy_new
— MethodEdited Compute Accuracy [Still needs to be nested within Fixed-Point Iteration]
ActiveInference.construct_policies_full
— MethodConstruct Policies
ActiveInference.dot_likelihood
— MethodDot-Product Function
ActiveInference.entropy_A
— MethodFunction for Calculating Entropy of A-Matrix
ActiveInference.fixed_point_iteration
— MethodRun State Inference via Fixed-Point Iteration
ActiveInference.generate_random_GM
— MethodGenerate Random Generative Model as A and B matrices
ActiveInference.get_expected_obs
— MethodGet Expected Observations
ActiveInference.get_expected_states
— MethodGet Expected States
ActiveInference.get_joint_likelihood
— MethodGet Joint Likelihood
ActiveInference.get_log_action_marginals
— MethodFunction to get log marginal probabilities of actions
ActiveInference.get_model_dimensions
— FunctionGet Model Dimensions from either A or B Matrix
ActiveInference.infer_policies!
— MethodUpdate the agents's beliefs over policies
ActiveInference.infer_states!
— MethodUpdate the agents's beliefs over states
ActiveInference.init_aif
— MethodInitialize Active Inference Agent function initaif( A, B; C=nothing, D=nothing, E = nothing, pA = nothing, pB = nothing, pD = nothing, parameters::Union{Nothing, Dict{String,Real}} = nothing, settings::Union{Nothing, Dict} = nothing, savehistory::Bool = true)
Arguments
- 'A': Relationship between hidden states and observations.
- 'B': Transition probabilities.
- 'C = nothing': Prior preferences over observations.
- 'D = nothing': Prior over initial hidden states.
- 'E = nothing': Prior over policies. (habits)
- 'pA = nothing':
- 'pB = nothing':
- 'pD = nothing':
- 'parameters::Union{Nothing, Dict{String,Real}} = nothing':
- 'settings::Union{Nothing, Dict} = nothing':
- 'settings::Union{Nothing, Dict} = nothing':
ActiveInference.kl_divergence
— MethodFunction for getting KL-divergence
ActiveInference.norm_dist
— MethodNormalizes a Categorical probability distribution
ActiveInference.norm_dist_array
— MethodNormalizes muliple arrays
ActiveInference.onehot
— MethodCreates a onehot encoded vector
ActiveInference.process_observation
— MethodProcess Observation to the Correct Format
ActiveInference.sample_action!
— MethodSample action from the beliefs over policies
ActiveInference.sample_action
— MethodSample Action [Stochastic or Deterministic]
ActiveInference.sample_category
— MethodSampling Function
ActiveInference.select_highest
— MethodSelects the highest value from Array – used for deterministic action sampling
ActiveInference.softmax
— MethodSoftmax Function
ActiveInference.softmax_array
— MethodSoftmax Function for array of arrays
ActiveInference.spm_MDP_G
— MethodCalculate Bayesian Surprise
ActiveInference.spm_cross
— FunctionMulti-dimensional outer product
ActiveInference.spm_log_array_any
— MethodApply spm_log to array of arrays
ActiveInference.spm_wnorm
— MethodSPM_wnorm
ActiveInference.to_array_of_any
— MethodEquivalent to pymdp's "toobjarray"
ActiveInference.update_A!
— MethodUpdate A-matrix
ActiveInference.update_B!
— MethodUpdate B-matrix
ActiveInference.update_D!
— MethodUpdate D-matrix
ActiveInference.update_obs_likelihood_dirichlet
— MethodUpdate obs likelihood matrix
ActiveInference.update_posterior_policies
— FunctionUpdate Posterior over Policies
ActiveInference.update_posterior_states
— MethodUpdate Posterior States
ActiveInference.update_state_likelihood_dirichlet
— MethodUpdate state likelihood matrix
ActiveInference.update_state_prior_dirichlet
— MethodUpdate prior D matrix