Bayesian ascent Monte Carlo Options: :predict-candidates (false by default) - output all samples rather than just those with increasing log-weight
Bayesian ascent Monte Carlo Options: :predict-candidates (false by default) - output all samples rather than just those with increasing log-weight
(->entry bandit-id value past-reward)
Positional factory function for class anglican.bamc.entry.
Positional factory function for class anglican.bamc.entry.
(->multiarmed-bandit arms new-arm-belief new-arm-count new-arm-drawn)
Positional factory function for class anglican.bamc.multiarmed-bandit.
Positional factory function for class anglican.bamc.multiarmed-bandit.
(add-bandit-predict state)
add bandit arms and counts as a predict
add bandit arms and counts as a predict
(add-trace-predict state)
adds trace as a predict
adds trace as a predict
(backpropagate state)
back propagate reward to bandits
back propagate reward to bandits
Bayesian belief
Bayesian belief
(bb-as-prior belief)
returns a belief for use as a prior belief
returns a belief for use as a prior belief
(bb-sample belief)
returns a random sample from the belief distribution
returns a random sample from the belief distribution
(bb-sample-mean belief)
returns a random sample from the mean belief distribution
returns a random sample from the mean belief distribution
(bb-update belief evidence)
updates belief based on the evidence
updates belief based on the evidence
uninformative mean reward belief
uninformative mean reward belief
initial state for MAP estimation
initial state for MAP estimation
(map->entry m__7585__auto__)
Factory function for class anglican.bamc.entry, taking a map of keywords to field values.
Factory function for class anglican.bamc.entry, taking a map of keywords to field values.
(map->multiarmed-bandit m__7585__auto__)
Factory function for class anglican.bamc.multiarmed-bandit, taking a map of keywords to field values.
Factory function for class anglican.bamc.multiarmed-bandit, taking a map of keywords to field values.
(not-a-value? value)
true when new value must be sampled
true when new value must be sampled
(record-choice state bandit-id value past-reward)
records random choice in the state
records random choice in the state
(reward-belief sum sum2 cnt)
returns reification of bayesian belief about the mean reward of an arm
returns reification of bayesian belief about the mean reward of an arm
(select-value bandit log-p)
selects value corresponding to the best arm
selects value corresponding to the best arm
(update-bandit bandit value reward)
updates bandit's belief
updates bandit's belief
cljdoc is a website building & hosting documentation for Clojure/Script libraries
× close