Robust-Multitask-RL
Robust-Multitask-RL copied to clipboard
Machine Learning Course Project Skoltech 2018
Results
1
Robust-Multitask-RL issues
Sort by
recently updated
recently updated
newest added
I found the RL algorithm in this code is DQN, but DQN can only apply in environments with discrete action space. What about environments with continuous action space?