Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks
Authors:
- Luca MarzariLMLuca Marzari
- Ameya PoreAPAmeya Pore
- Diego Dall'AlbaDDDiego Dall'Alba
- Gerardo Aragon-CamarasaGAGerardo Aragon-Camarasa
- Alessandro FarinelliAFAlessandro Farinelli
- Paolo FioriniPFPaolo Fiorini
Preprint
Abstract
Deep Reinforcement Learning (DRL) is emerging as a promising approach to generate adaptive behaviors for robotic platforms. However, a major drawback of using DRL is the data-hungry training regime that requires millions of trial and error attempts, which is impractical when running experiments on robotic systems. Learning from Demonstrations (LfD) has been introduced to solve this issue by cloning the behavior of expert demonstrations. However, LfD requires a large number of demonstrations that are difficult to be acquired since dedicated complex setups are required. To overcome these limitations, we propose a multi-subtask reinforcement learning methodology where complex pick and place tasks can be decomposed into low-level subtasks. These subtasks are parametrized as expert networks and learned via DRL methods. Trained subtasks are then combined by a high-level choreographer to accomplish the intended pick and place task considering different initial configurations. As a testbed, we use a pick and place robotic simulator to demonstrate our methodology and show that our method outperforms a benchmark methodology based on LfD in terms of sample-efficiency. We transfer the learned policy to the real robotic system and demonstrate robust grasping using various geometric-shaped objects.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Learning from Demonstrations for Autonomous Soft-tissue Retraction2021
- Multi-expert learning of adaptive legged locomotionScience Robotics, 2020
- Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments2020
- Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulation2019
- Learning to Walk Via Deep Reinforcement Learning2019
- Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collectionThe International Journal of Robotics Research, 2017
- Recent Advances in Hierarchical Reinforcement LearningDiscrete Event Dynamic Systems, 2003
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991