We present the theory behind a novel unsupervised method for discovering quasi-static objects, objects that are stationary during some interval of observation, within image sequen...
Brandon C. S. Sanders, Randal C. Nelson, Rahul Suk...
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
— Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the environment. Constraints are usually unobservable and frequently...
Matthew Howard, Stefan Klanke, Michael Gienger, Ch...
Perfect recall is the common and natural assumption that an agent never forgets. As a consequence, the agent can always condition its choice of action on any prior observations. I...
Kevin Waugh, Martin Zinkevich, Michael Johanson, M...