BY571/Soft-Actor-Critic-and-Extensions
PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.
PythonMIT
Issues
- 0
IndexError: deque already at its maximum size
#10 opened by zdf1840 - 0
why the result is not good?
#9 opened by wangchangquan - 0
where is the Munchausen RL?
#7 opened by wangchangquan - 0
Münchhausen reward not matching paper?
#8 opened by slerman12 - 1
Can not find the Munchausen SAC!
#6 opened by lknownothing - 1
understanding alpha learning
#3 opened by shuangwu - 0
Use of sum trees
#5 opened by yk287 - 6
UserWarning
#4 opened by ChenyangRan - 1
minor errors in the code of SAC.py
#2 opened by TAOGZ - 1
How do you plot figures?
#1 opened by sweetice