Proximal Policy Optimization

model-free reinforcement learning algorithm

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

Категорії:

policy-gradient methodmodel-free reinforcement learning