2.3k citations · 3.1k across the 16 of their papers we have counts for
16 papers
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
Samin Yeasar Arnob, Scott Fujimoto, Doina Precup
In this paper, we investigate the use of small datasets in the context of offline reinforcement learning (RL). While many common offline RL benchmarks employ datasets with over a m…
Fairness in Reinforcement Learning with Bisimulation Metrics
Sahand Rezaei-Shoshtari, Hanna Yurchyk, Scott Fujimoto +2
Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without co…
Generalizable Imitation Learning Through Pre-Trained Representations
Wei-Di Chang, Francois Hogan, Scott Fujimoto +2
In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. W…
Imitation Learning from Observation through Optimal Transport
Wei-Di Chang, Scott Fujimoto, David Meger +1
Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance…
For SALE: State-Action Representation Learning for Deep Reinforcement Learning
Scott Fujimoto, Wei-Di Chang, Edward J. Smith +3
In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states,…
IL-flOw: Imitation Learning from Observation using Normalizing Flows
Wei-Di Chang, Juan Camilo Gamboa Higuera, Scott Fujimoto +2
We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-…
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
Scott Fujimoto, David Meger, Doina Precup +2
In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy. While the Bellman equation is uniquely solved by the true value funct…
A Minimalist Approach to Offline Reinforcement Learning
Scott Fujimoto, Shixiang Shane Gu
Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL alg…
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
Scott Fujimoto, David Meger, Doina Precup
Marginalized importance sampling (MIS), which measures the density ratio between the state-action occupancy of a target policy and that of a sampling distribution, is a promising a…
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
Scott Fujimoto, David Meger, Doina Precup
Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their te…
Benchmarking Batch Deep Reinforcement Learning Algorithms
Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh +1
Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following…
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward J. Smith, Scott Fujimoto, Adriana Romero +1
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined…
Off-Policy Deep Reinforcement Learning without Exploration
Scott Fujimoto, David Meger, Doina Precup
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for…
Horizon: Facebook's Open Source Applied Reinforcement Learning Platform
Jason Gauci, Edoardo Conti, Yitao Liang +7
In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL probl…
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
Edward Smith, Scott Fujimoto, David Meger
We consider the problem of scaling deep generative shape models to high-resolution. Drawing motivation from the canonical view representation of objects, we introduce a novel metho…
Addressing Function Approximation Error in Actor-Critic Methods
Scott Fujimoto, Herke van Hoof, David Meger
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We…