Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning (1802.04520v2)

Abstract: We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally across a set of similar environments, each with dynamics drawn from a prior distribution. We propose that the agent is able to adjust its actions almost immediately, based on small set of observations. This robust and adaptive behavior is enabled by using a policy gradient algorithm with an Long Short Term Memory (LSTM) function approximation. Finally, we train an agent to navigate a two-dimensional environment with uncertain dynamics and noisy observations. We demonstrate that this agent has good zero-shot performance in a real physical environment. Our preliminary results indicate that the agent is able to infer the environmental dynamics after only a few timesteps, and adjust its actions accordingly.