3.10. SequentialLearning.Comap
From the authors
Transport of algorithms and environments
Main definitions
-
Round.map fo fa fy,Hist.map fo fa fy: round-wise transport of a round and a history along maps of the observation, the action and the feedback, with the special casesmapObs,mapActionandmapFeedbackthat transport a single component. -
Algorithm.comap alg F hF: the algorithm that transforms the pair (past rounds, current observation) by the measurable mapF nat roundnbefore applying the policy ofalg. -
Algorithm.comapObs alg f: the algorithm that seesf owhen the observation iso, both in the current round and in the past rounds. -
Algorithm.comapFeedback alg g: the algorithm that seesg ywhen the feedback of a past round isy. -
Environment.comap env F hF f hf: the environment that reads the summaryF nof the past rounds and readsf awhen the algorithm playsain the current round. -
Environment.comapAction env f: the environment that readsf awhen the algorithm playsa, both in the current round and in the past rounds. -
Algorithm.congr alg e𝓞 e𝓐 e𝓨,Environment.congr env e𝓞 e𝓐 e𝓨: relabelling of the observations, the actions and the feedbacks of a player along measurable equivalences.
Main statements
-
IsAlgEnvSeq.hasCondDistrib_action_comapObs,IsAlgEnvSeq.hasCondDistrib_action_comapFeedback: in a run ofalg.comapObs f(resp.alg.comapFeedback g) against any environment, the conditional distribution of the action given the transported history and the transported observation isalg.policy n. -
IsAlgEnvSeq.hasCondDistrib_obs_comapAction,IsAlgEnvSeq.hasCondDistrib_feedback_comapAction: in a run againstenv.comapAction f, the observations and feedbacks have the conditional distributions of a run ofenvon the transported actions.
Module LeanMachineLearning.SequentialLearning.Comap contains 69 exposed declarations.
-
Learning.Round.map -
Learning.Hist.map -
Learning.Round.obs_map -
Learning.Round.action_map -
Learning.Round.feedback_map -
Learning.Hist.map_apply -
Learning.Round.map_id -
Learning.Hist.map_id -
Learning.Round.map_comp -
Learning.Hist.map_comp -
Learning.Round.measurable_map -
Learning.Hist.measurable_map -
Learning.Round.mapObs -
Learning.Hist.mapObs -
Learning.Round.mapAction -
Learning.Hist.mapAction -
Learning.Round.mapFeedback -
Learning.Hist.mapFeedback -
Learning.Algorithm.comap -
Learning.Algorithm.policy_comap -
Learning.Algorithm.p0_comap -
Learning.Algorithm.comap_id -
Learning.Algorithm.comap_comap -
Learning.Algorithm.comapObs -
Learning.Algorithm.comapObs_def -
Learning.Algorithm.policy_comapObs -
Learning.Algorithm.p0_comapObs -
Learning.Algorithm.comapObs_id -
Learning.Algorithm.comapObs_comapObs -
Learning.Algorithm.comapFeedback -
Learning.Algorithm.comapFeedback_def -
Learning.Algorithm.policy_comapFeedback -
Learning.Algorithm.p0_comapFeedback -
Learning.Algorithm.comapFeedback_id -
Learning.Algorithm.comapFeedback_comapFeedback -
Learning.Algorithm.comapObs_comapFeedback_comm -
Learning.Environment.comap -
Learning.Environment.obs_comap -
Learning.Environment.feedback_comap -
Learning.Environment.obs0_comap -
Learning.Environment.ν0_comap -
Learning.Environment.comap_id -
Learning.Environment.comap_comp -
Learning.Environment.comapAction -
Learning.Environment.comapAction_def -
Learning.Environment.obs_comapAction -
Learning.Environment.feedback_comapAction -
Learning.Environment.obs0_comapAction -
Learning.Environment.ν0_comapAction -
Learning.Environment.comapAction_id -
Learning.Environment.comapAction_comp -
Learning.Algorithm.congr -
Learning.Algorithm.policy_congr -
Learning.Algorithm.p0_congr -
Learning.Algorithm.congr_refl -
Learning.Algorithm.congr_congr -
Learning.Algorithm.congr_symm -
Learning.Environment.congr -
Learning.Environment.obs_congr -
Learning.Environment.feedback_congr -
Learning.Environment.obs0_congr -
Learning.Environment.ν0_congr -
Learning.Environment.congr_refl -
Learning.Environment.congr_congr -
Learning.Environment.congr_symm -
Learning.IsAlgEnvSeq.hasCondDistrib_action_comapObs -
Learning.IsAlgEnvSeq.hasCondDistrib_action_comapFeedback -
Learning.IsAlgEnvSeq.hasCondDistrib_obs_comapAction -
Learning.IsAlgEnvSeq.hasCondDistrib_feedback_comapAction