activity
20122022
most citedProceedings of the 29th International Conference on Machine Learning (ICML-12)

1.6k citations · 2.2k across the 30 of their papers we have counts for

collaborators
Showing cs.LGShow all

52 papers · 1 filter

cs.LG2022

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

Lucas Caccia, Rahaf Aljundi, Nader Asadi +3

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small sub…

cs.LG2022★ 1 cited

Robust Policy Learning over Multiple Uncertainty Sets

Annie Xie, Shagun Sodhani, Chelsea Finn +2

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from on…

cs.LG2022

A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions

Anthony GX-Chen, Veronica Chelu, Blake A. Richards +1

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value func…

cs.LG2021★ 3 cited

Block Contextual MDPs for Continual Learning

Shagun Sodhani, Franziska Meier, Joelle Pineau +1

In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationary. This assumption of stationarity, whi…

cs.LG2021★ 1 cited

Correcting Momentum in Temporal Difference Learning

Emmanuel Bengio, Joelle Pineau, Doina Precup

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We arg…

cs.LG2021★ 5 cited

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Harsh Satija, Philip S. Thomas, Joelle Pineau +1

We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning (RL) setting. We consider the scenario where: (i) we have a dataset co…