In a previous post, we train an Agent using Deep Reinforcement Learning to win a game limited to the middle lane. In the case of Dota2 that has large the state and action, training takes a minimum 1 week even if the map area, hero number are limited. We can…

In the previous post, I created two model needed to create Deep Learning agent for Minecraft.

In the previous two posts, we prepare the basic component what we need to train the large scale MOBA game using the Deep Reinforcement Learning. In this post, we will see how to combine the code of Dota2 and Seed RL. You can find a code for this post at…

In the last post, we learn how to train a simple MOBA game using Deep Reinforcement Learning. In this post, I am going to explain what we need to know before applying the same method to the Dota2. Code for this post can be found here: https://github.com/kimbring2/MOBA_RL/blob/main/dota2/env_test.py You just need…

The MOBA are currently one of the most popular game genres along with RTS and MMORPG. Unlike RTS games, MOBA games have a fixed number of units that can be controlled by the user. However, the unit can grow up through level and item system as the game progresses. …

In the past post, I showed how to solve one of the minigames of PySC2 using the Actor-Critic Reinforcement Learning algorithm. In the case of a minigame that has a simple structure, the agent does not need human expert data for behavior cloning. However, in the case of an actual…

Due to the memory limitations of LSTMs, most of the current Deep Learning models have used attention mechanisms. A paper titled ‘Deep reinforcement learning with relational inductive biases’ about that topic was already published by DeepMind at ICLR 2019. Relational environment In this paper, grid type environment is used to verify the…

I tried various attempts to implement the AlphaStar paper. However, I could not check any meaningful training results because of the huge size of the model. …

Starcraft 2 uses a multiple states and actions unlike the Atari games used for Deep Learning research. For that reason, agent of Starcraft 2 should have multiple Neural Networks unlike agent of Atari game which has only 1 Encoder network for state, head network for action. Network Architecture There are a total…