9 citations · 12 across the 8 of their papers we have counts for
9 papers
Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs
Michael Gimelfarb, Ayal Taitler, Scott Sanner
We propose the Constraint-Generation Policy Optimization (CGPO) framework to optimize policy parameters within compact and interpretable policy classes for mixed discrete-continuou…
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
Michael Gimelfarb, Michael Jong Kim
We study parameterized MDPs (PMDPs) in which the key parameters of interest are unknown and must be learned using Bayesian inference. One key defining feature of such models is the…
pyRDDLGym: From RDDL to Gym Environments
Ayal Taitler, Michael Gimelfarb, Jihwan Jeong +4
We present pyRDDLGym, a Python framework for auto-generation of OpenAI Gym environments from RDDL declerative description. The discrete time step evolution of variables in RDDL is…
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization
Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb +3
Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approa…
RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation
Noah Patton, Jihwan Jeong, Michael Gimelfarb +1
Planning provides a framework for optimizing sequential decisions in complex environments. Recent advances in efficient planning in deterministic or stochastic high-dimensional dom…
Risk-Aware Transfer in Reinforcement Learning using Successor Features
Michael Gimelfarb, André Barreto, Scott Sanner +1
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer le…