Starcraft 2 updating blizzard update agent
From a reinforcement learning perspective, Star Craft II also offers an unparalleled opportunity to explore many challenging new frontiers: Py SC2 is Deep Mind's Python component of the Star Craft II Learning Environment (SC2LE).
It exposes Blizzard Entertainment's Star Craft II Machine Learning API as a Python reinforcement learning (RL) Environment.
The series goes through the following topics: The algorithm of choice for the most successful implementations of Reinforcement Learning agent for Star Craft II seems to be A3C .
We have worked on top of two implementations of A3C: one by Xiaowei Hu; and another by Lim Swee Kiat, which at the same time is based on top of Juliani's tutorials on Reinforcement Learning with Tensor Flow .
This project was developed during the Deep Learning for Artificial Intelligence Course at UPC Telecom BCN, Autumn 2017.
This was presented in the DLAI session of 2017/12/12. As defined on the Blizzard website (the company that develops the game): Star Craft II: Wings of Liberty is the long-awaited sequel to the original Star Craft, Blizzard Entertainment’s critically acclaimed sci-fi real-time strategy (RTS) game.
Then, it is enough to take the action that maximizes the utility from the current state (i.e. Similarly to Q learning, it is often unfeasible to store the support function (either the Q values or the policy) in a table, so a function approximator is employed.A3C is short for Asynchronous Advantage Actor Critic and belongs to the family of the so-called Actor-Critic (from now on, just AC) algorithms inside Reinforcement Learning.AC algorithms maintain and update a stochastic policy.The armies in play can be as small as a single squad of Marines or as large as a full-blown planetary invasion force.As commander, you observe the battlefield from a top-down perspective and issue orders to your units in real time.