Jump-Start Reinforcement Learning
This addresses a bottleneck in RL for tasks like simulated robotics by enabling more efficient policy initialization, though it is an incremental improvement over existing RL methods.
The paper tackles the problem of inefficient learning in reinforcement learning (RL) from scratch, especially in tasks with exploration challenges, by proposing Jump-Start Reinforcement Learning (JSRL), a meta algorithm that uses a guide-policy to initialize an RL policy and significantly outperforms existing methods, particularly in small-data regimes, with sample complexity improved from exponential to polynomial in horizon.
Reinforcement learning (RL) provides a theoretical framework for continuously improving an agent's behavior via trial and error. However, efficiently learning policies from scratch can be very difficult, particularly for tasks with exploration challenges. In such settings, it might be desirable to initialize RL with an existing policy, offline data, or demonstrations. However, naively performing such initialization in RL often works poorly, especially for value-based methods. In this paper, we present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy, and is compatible with any RL approach. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks: a guide-policy, and an exploration-policy. By using the guide-policy to form a curriculum of starting states for the exploration-policy, we are able to efficiently improve performance on a set of simulated robotic tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms, particularly in the small-data regime. In addition, we provide an upper bound on the sample complexity of JSRL and show that with the help of a guide-policy, one can improve the sample complexity for non-optimism exploration methods from exponential in horizon to polynomial.