22 Commits (62c1198f250e6492244c5548392a53d093f8241b)

Author SHA1 Message Date
Thomas Knoll 5dcabef8e0 added utils classes 2 years ago
Thomas Knoll ae94b57876 changed iteration handling 2 years ago
Thomas Knoll 45d110b199 added probability arguments 2 years ago
Thomas Knoll 5c9064ecbe randomize start 2 years ago
Thomas Knoll 80cbbe5a3a minor changes 2 years ago
Thomas Knoll 906f251401 some fixes to key and door handling 3 years ago
Thomas Knoll 1528173f58 changed iterations to evaluations 3 years ago
Thomas Knoll 8650b7c91f added tune example 3 years ago
Thomas Knoll 3dee543e24 renaming and notebooks 3 years ago
Thomas Knoll 138d917fd6 added tune example 3 years ago
Thomas Knoll e2c855dc6a added more shielding options 3 years ago
Thomas Knoll f3747a1479 renaming / shield handling changes 3 years ago
Thomas Knoll 757fbbcc0d fixed shield generation 3 years ago
Thomas Knoll 1c2dbf706e changed shield creation to create shield on reset 3 years ago
Thomas Knoll 97f7d23cda added rudimental key / door masking 3 years ago
Thomas Knoll b1b014dbd6 some refactoring as preparation for sb3 example 3 years ago
Thomas Knoll fab1e8f23f added logdir handling 3 years ago
Thomas Knoll 7f20c3f909 arguments and log dir 3 years ago
Thomas Knoll fe96a6a0b6 added dqn algorithm 3 years ago
Thomas Knoll e42becef88 added dqn handling skeleton 3 years ago
Thomas Knoll f52262ad11 simple masking (only turn left allowed) 3 years ago
Thomas Knoll cf18349819 basic action embedding 3 years ago
Thomas Knoll dd9dd43036 initial layout for rl test 3 years ago