Automata Guided Reinforcement Learning With Demonstrations
arXiv:1809.06305
Abstract
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We propose to address these problems by combining temporal logic (TL) with reinforcement learning from demonstrations. Our method automatically generates intrinsic rewards that align with the overall task goal given a TL task specification. The policy resulting from our framework has an interpretable and hierarchical structure. We validate the proposed method experimentally on a set of robotic manipulation tasks.
References in corpus (8)
- Continuous control with deep reinforcement learning
- DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
- Modular Multitask Reinforcement Learning with Policy Sketches
- Reinforcement and Imitation Learning for Diverse Visuomotor Skills
- TACO: Learning Task Decomposition via Temporal Alignment for Control
- Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks