Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
This addresses the problem of inefficient exploration in sparse reward settings for reinforcement learning agents, offering a novel hierarchical approach that is not incremental but introduces a new intrinsic reward type.
The paper tackles the challenge of exploration in sparse reward reinforcement learning by learning separate intrinsic and extrinsic task policies and scheduling between them, resulting in substantially improved exploration efficiency across three visual input environments.
Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration. Commonly these signals are added as bonus rewards, which results in a mixture policy that neither conducts exploration nor task fulfillment resolutely. In this paper, we instead learn separate intrinsic and extrinsic task policies and schedule between these different drives to accelerate exploration and stabilize learning. Moreover, we introduce a new type of intrinsic reward denoted as successor feature control (SFC), which is general and not task-specific. It takes into account statistics over complete trajectories and thus differs from previous methods that only use local information to evaluate intrinsic motivation. We evaluate our proposed scheduled intrinsic drive (SID) agent using three different environments with pure visual inputs: VizDoom, DeepMind Lab and DeepMind Control Suite. The results show a substantially improved exploration efficiency with SFC and the hierarchical usage of the intrinsic drives. A video of our experimental results can be found at https://youtu.be/b0MbY3lUlEI.