Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results. (arXiv:2107.04982v2 [cs.LG] UPDATED)

We study the problem of out-of-distribution dynamics (OODD) detection, which
involves detecting when the dynamics of a temporal process change compared to
the training-distribution dynamics. This is relevant to applications in
control, reinforcement learning (RL), and multi-variate time-series, where
changes to test time dynamics can impact the performance of learning
controllers/predictors in unknown ways. This problem is particularly important
in the context of deep RL, where learned controllers often overfit to the
training environment. Currently, however, there is a lack …

arxiv benchmarks detection distribution dynamics rl