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 performance of the model. However, it is confirmed that that environment takes too much time to train compared to the quality of it due to the way of moving the block. That is why I decide to use another environment that has relational features but has a simple movement way. After confirming whether the algorithm of the paper works, we can use it in the Starcraft 2 environment.

…

#reinforcement-learning #relational-intelligence #tensorflow #deep-learning #relational deep reinforcement learning