uDDPG: Monte-Carlo version of DDPG for BipedalWalker-v3 environment

I wrote the book with a careful explanation, it is in the 4th section, Paperback version (not eBook): https://www.amazon.com/dp/B0CKYWHPF5

This outdated paper contains various experiments and complicated, but the code here is up-to-date and simplified. https://ieeexplore.ieee.org/document/9945743

T. Ishuov, Z. Otarbay and M. Folgheraiter, "A Concept of Unbiased Deep Deterministic Policy Gradient for Better Convergence in Bipedal Walker," 2022 International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan, 2022, pp. 1-6, doi: 10.1109/SIST54437.2022.9945743.

Epsilon decreases in Actor with exponential decay: 3e^-x Ackowledgements: my heart belongs to Jesus Christ.