12 citations · 82 across the 18 of their papers we have counts for
33 papers
Transfer RL via the Undo Maps Formalism
Abhi Gupta, Ted Moskovitz, David Alvarez-Melis +1
Transferring knowledge across domains is one of the most fundamental problems in machine learning, but doing so effectively in the context of reinforcement learning remains largely…
Learning General World Models in a Handful of Reward-Free Deployments
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano +5
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate…
Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai +2
Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial fo…
Meta Learning MDPs with Linear Transition Models
Robert Müller, Aldo Pacchiano
We study meta-learning in Markov Decision Processes (MDP) with linear transition models in the undiscounted episodic setting. Under a task sharedness metric based on model proximit…
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano +3
We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first de…
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan +1
Reinforcement learning (RL) is empirically successful in complex nonlinear Markov decision processes (MDPs) with continuous state spaces. By contrast, the majority of theoretical R…