reinforcement_learning issueshttps://git.rwth-aachen.de/groups/monticore/EmbeddedMontiArc/applications/reinforcement_learning/-/issues2022-10-05T15:41:29+02:00https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/applications/reinforcement_learning/coopmontisimautopilot/-/issues/3Check Reward2022-10-05T15:41:29+02:00Evgeny KusmenkoCheck Reward- Please check if reward calculated by simulator equals the one received and used in training
- please check if action computed by the actor is the same as received by the simulator- Please check if reward calculated by simulator equals the one received and used in training
- please check if action computed by the actor is the same as received by the simulatorRodion PrikhodovskyTil MohrRodion Prikhodovsky2022-09-30https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/applications/reinforcement_learning/coopmontisimautopilot/-/issues/2Update Readme.md2022-10-06T17:52:03+02:00Evgeny KusmenkoUpdate Readme.md- mention in readme.md:
- problem with GPU training on cluster
-- mention in readme.md:
- problem with GPU training on cluster
-Rodion PrikhodovskyTil MohrRodion Prikhodovsky