An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies
This addresses the challenge of efficient exploration for agents in environments without rewards, which is incremental as it builds on existing exploration methods with a novel objective.
The paper tackles the problem of learning exploration policies without external rewards by proposing a surrogate objective that maximizes a lower bound to the entropy of the steady-state distribution, leading to highly exploring and fast mixing policies. The result is the IDE$^{3}$AL algorithm, which is empirically evaluated on hard-exploration tasks, though no concrete numbers are provided in the abstract.
What is a good exploration strategy for an agent that interacts with an environment in the absence of external rewards? Ideally, we would like to get a policy driving towards a uniform state-action visitation (highly exploring) in a minimum number of steps (fast mixing), in order to ease efficient learning of any goal-conditioned policy later on. Unfortunately, it is remarkably arduous to directly learn an optimal policy of this nature. In this paper, we propose a novel surrogate objective for learning highly exploring and fast mixing policies, which focuses on maximizing a lower bound to the entropy of the steady-state distribution induced by the policy. In particular, we introduce three novel lower bounds, that lead to as many optimization problems, that tradeoff the theoretical guarantees with computational complexity. Then, we present a model-based reinforcement learning algorithm, IDE$^{3}$AL, to learn an optimal policy according to the introduced objective. Finally, we provide an empirical evaluation of this algorithm on a set of hard-exploration tasks.