Closed m09 closed 4 years ago
Relational Deep Reinforcement Learning by DeepMind, published at ICLR 2019 (poster)
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during training, and overall performance. In the StarCraft II Learning Environment, our agent achieves state-of-the-art performance on six mini-games – surpassing human grandmaster performance on four. By considering architectural inductive biases, our work opens new directions for overcoming important, but stubborn, challenges in deep RL.
I'm going to be opening a vote on the https://forum.sourced.tech/c/sourced-reading-club soon
Next paper candidates
Let's propose papers to study next! All papers mentioned in the comments of this issue will be listed in the next vote.
Last session runner-up(s)
Topology Adaptive Graph Convolutional Networks
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters