AMPED
PublicReinforcement learning algorithm that blends the N-th order Markov property with abstract MDPs, PPO, and a hybrid model-free/model-based approach.
Creat:2020-11-06T12:59:02
Update:2024-04-23T14:41:49
0
Stars
0
Stars Increase
Reinforcement learning algorithm that blends the N-th order Markov property with abstract MDPs, PPO, and a hybrid model-free/model-based approach.