D4PG-ray
PublicDistributed PyTorch implementation of D4PG with ray. Using a SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.
continuous-action-spaced4pgddpgdistributed-computingiqnrayreinforcement-learningreinforcement-learning-algorithmsstate-of-the-art
Creat:2020-12-30T05:54:25
Update:2024-08-23T18:03:19
2
Stars
0
Stars Increase