Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning
This work addresses the challenge of achieving robust reinforcement learning in multi-robot systems with heterogeneous real-world perturbances, setting a foundation for future methods, though it is incremental as it builds on existing PPO and simulation-based analysis.
The paper tackles the problem of bridging the simulation-to-reality gap in collaborative multi-robot deep reinforcement learning by analyzing how sensing, calibration, and accuracy mismatches affect learning with proximal policy optimization (PPO) in simulations using a Kuka arm model, finding that the type and number of perturbances impact collaborative learning efforts.
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.