dhruvramani/Transformers-RL
An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"
PythonMIT
Issues
- 0
Bugs report about memory mechanism
#7 opened by TimerChen - 1
u and v may be NaN from the beginning
#3 opened by VanillaWhey - 0
A question about the function update_memory
#6 opened by HarPoon0 - 0
How to combine it with PPO algorithm?
#5 opened by borninfreedom