A Notation for Markov Decision Processes

19 citations recorded by the source corpus.

This paper specifies a notation for Markov decision processes.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (2016, methodology): “We used three domains: a 4 × 4 gridworld previously constructed speciﬁcally for evaluating OPE meth-ods (Thomas, 2015b, Section 2.5), as well as two simple domains that we developed to exemplify the settings where different methods excel and fail.”
Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing (2017, methodology): “We use the notational standard MDPNv1 (Thomas, 2015) for MDPs.”
Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines (2017, methodology): “We use the notational standard MDPNv1 (Thomas and Okal, 2015) and the following additional deﬁnitions, where expectations conditioned on θ denote that actions, A t , are sampled from π ( S t , · , θ ) unless otherwise speciﬁed: Objective function: State-action value function: Discounted state distri”
Active Reinforcement Learning: Observing Rewards at a Cost (2020, methodology): “;0 that is known to 2An index strategy computes for each arm a number that is independent of the other arms and takes the action with highest number. 3We use the notational standard MDPNv1 (Philip S. Thomas, 2015) 4 0 2000 4000 6000 8000 10000 time steps 0 500 1000 1500 2000 2500 average cumulative ”