RewardShifting
PublicCode for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL
deep-q-networkdqn-rndensembleensemble-learningensemble-rlexploration-exploitationoffline-reinforcement-learningreinforcement-learningreward-designreward-engineering
Creat:2022-05-16T03:51:37
Update:2024-12-27T14:56:26
https://sites.google.com/view/rewardshaping
29
Stars
0
Stars Increase