Reinforcement Learning
Model-based Policy Optimization with Unsupervised Model Adaptation
In recent years, model-free reinforcement learning (MFRL) has achieved tremendous success on a wide range of simulated domains, e .
MinimaxValueIntervalforOff-PolicyEvaluation andPolicyOptimization
FunctionApproximation Throughout thepaper,weassume access totwofunction classesQ (S A R)andW (S A R). Todevelop intuition, theyare supposed to modelQπ and wπ/µ, respectively, though most of our main results are stated without assuming any kind of realizability.
MinimaxValueIntervalforOff-PolicyEvaluation andPolicyOptimization
FunctionApproximation Throughout thepaper,weassume access totwofunction classesQ (S A R)andW (S A R). Todevelop intuition, theyare supposed to modelQπ and wπ/µ, respectively, though most of our main results are stated without assuming any kind of realizability.
