Reinforced Grounded Action Transformation for Sim-to-Real Transfer
This addresses the reality gap in robotics for incremental improvement over existing methods like GAT.
The paper tackles the sim-to-real transfer problem for robots by introducing Reinforced Grounded Action Transformation (RGAT), which uses reinforcement learning to ground the simulator end-to-end, resulting in successful transfer for neural network policies in MuJoCo domains.
Robots can learn to do complex tasks in simulation, but often, learned behaviors fail to transfer well to the real world due to simulator imperfections (the reality gap). Some existing solutions to this sim-to-real problem, such as Grounded Action Transformation (GAT), use a small amount of real-world experience to minimize the reality gap by grounding the simulator. While very effective in certain scenarios, GAT is not robust on problems that use complex function approximation techniques to model a policy. In this paper, we introduce Reinforced Grounded Action Transformation(RGAT), a new sim-to-real technique that uses Reinforcement Learning (RL) not only to update the target policy in simulation, but also to perform the grounding step itself. This novel formulation allows for end-to-end training during the grounding step, which, compared to GAT, produces a better grounded simulator. Moreover, we show experimentally in several MuJoCo domains that our approach leads to successful transfer for policies modeled using neural networks.