Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning
arXiv:2008.07875
Abstract
Current research directions in deep reinforcement learning include bridging the simulation-reality gap, improving sample efficiency of experiences in distributed multi-agent reinforcement learning, together with the development of robust methods against adversarial agents in distributed learning, among many others. In this work, we are particularly interested in analyzing how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems where the operation of the different robots is not necessarily homogeneous. These variations can happen due to sensing mismatches, inherent errors in terms of calibration of the mechanical joints, or simple differences in accuracy. While our results are simulation-based, we introduce the effect of sensing, calibration, and accuracy mismatches in distributed reinforcement learning with proximal policy optimization (PPO). We discuss on how both the different types of perturbances and how the number of agents experiencing those perturbances affect the collaborative learning effort. The simulations are carried out using a Kuka arm model in the Bullet physics engine. This is, to the best of our knowledge, the first work exploring the limitations of PPO in multi-robot systems when considering that different robots might be exposed to different environments where their sensors or actuators have induced errors. With the conclusions of this work, we set the initial point for future work on designing and developing methods to achieve robust reinforcement learning on the presence of real-world perturbances that might differ within a multi-robot system.
Accepted to the 5th International Conference on Robotics and Automation Engineering, IEEE, 2020
References in corpus (7)
- Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
- Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
- Adversarial Policies: Attacking Deep Reinforcement Learning
- Blockchain-Powered Collaboration in Heterogeneous Swarms of Robots
- DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning
- Time-Varying Formation Controllers for Unmanned Aerial Vehicles Using Deep Reinforcement Learning
- Multi-Agent Deep Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks with Imperfect Channels