Partial Observability

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
We show empirically that the sample complexity and asymptotic performance of learned non-linear controllers in partially observable settings continues to follow theoretical limits based on the difficulty of state estimation
Jingxi Xu, Bruce Lee, Nikolai Matni, Dinesh Jayaraman
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
How to train RL agents safely? We propose to pretrain a model-based agent in a mix of sandbox environments, then plan pessimistically when finetuning in the target environment.
Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman