Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)
Why do you think that https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is a good alternative to HJxB
Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)
Why do you think that https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is a good alternative to HJxB