Proximal Policy Optimization

model-free reinforcement learning algorithm

en-GB/ˈpɹɒksɪməl ˈpɒləsɪ ɒptɪmaɪzeɪʃn/
en-US/ˈpɹɑksəməl ˈpɑlɪsi ɑptɪmɪˈzeɪʃən/

Κατηγορίες:

policy-gradient methodmodel-free reinforcement learning