SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning
This addresses the problem of limited exploration efficiency in off-policy reinforcement learning for researchers and practitioners, though it is incremental as it builds on existing behavioral prior methods.
The paper tackles the challenge of efficient exploration in deep reinforcement learning by introducing state-free priors that model temporal consistency from offline data, enabling acceleration in complex tasks even with simpler training data, achieving faster learning in long-horizon continuous control tasks with sparse rewards.
Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However, if the task at hand deviates excessively from the demonstrated task, the effectiveness of such methods is limited. In our work, we propose to learn features from offline data that are shared by a more diverse range of tasks, such as correlation between actions and directedness. Therefore, we introduce state-free priors, which directly model temporal consistency in demonstrated trajectories, and are capable of driving exploration in complex tasks, even when trained on data collected on simpler tasks. Furthermore, we introduce a novel integration scheme for action priors in off-policy reinforcement learning by dynamically sampling actions from a probabilistic mixture of policy and action prior. We compare our approach against strong baselines and provide empirical evidence that it can accelerate reinforcement learning in long-horizon continuous control tasks under sparse reward settings.