Reinforcement Learning
Inverse Reinforcement Learning from a Gradient-based Learner
Inverse Reinforcement Learning addresses the problem of inferring an expert's
Inverse Reinforcement Learning from a Gradient-based Learner
Inverse Reinforcement Learning addresses the problem of inferring an expert's
1b742ae215adf18b75449c6e272fd92d-Paper.pdf
In particular, we look at commonalities and differences between parametric models and experience replay.
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
David Janz, Jiri Hron, Przemysลaw Mazur, Katja Hofmann, Josรฉ Miguel Hernรกndez-Lobato, Sebastian Tschiatschek
Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL.
Forethought_and_Hindsight_in_Credit_Assignment__Camera_Ready_ (3).pdf
Credit assignment, i.e. determining how to correctly associate delayed rewards with states or state-action pairs, is a crucial problem for reinforcement learning (RL) agents ( Sutton and Barto, 2018).