Reinforcement Learning Algorithms with Python

Implementation of TD3

To put this strategy into code, we have to create two critics with different initializations, compute the target action value as in (8.7), and optimize both critics.

TD3 is applied on the DDPG implementation that we discussed in the previous section. The following snippets are only a portion of the additional code that is needed to implement TD3. The complete implementation is available in the GitHub repository of the book: https://github.com/PacktPublishing/Hands-On-Reinforcement-Learning-Algorithms-with-Python.

With regard to the double critic, you have just to create them by calling deterministic_actor_double_critic twice, once for the target and once for the online networks, as done in DDPG. The code will be similar ...