Unsupervised Control Through Non-Parametric Discriminative Rewards

David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni, Catalin Ionescu, Steven Hansen, Volodymyr Mnih

Abstract: Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable aspects of the environment instead of distance in the space of observations. We demonstrate the efficacy of our agent to learn, in an unsupervised manner, to reach a diverse set of goals on three domains -- Atari, the DeepMind Control Suite and DeepMind Lab.

Keywords: deep reinforcement learning, goals, UVFA, mutual information

TL;DR: Unsupervised reinforcement learning method for learning a policy to robustly achieve perceptually specified goals.

Data: [Arcade Learning Environment](https://paperswithcode.com/dataset/arcade-learning-environment), [DeepMind Control Suite](https://paperswithcode.com/dataset/deepmind-control-suite)