Paper
Publication
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness
Paper
Publication
Online Apprenticeship Learning
Paper
Publication
Chaining Value Functions for Off-Policy Learning
Paper
Publication
Introducing Symmetries to Black Box Meta Reinforcement Learning
Paper
Publication
Learning Expected Emphatic Traces for Deep RL
Paper
Publication
Analogy Training Multilingual Encoders
Paper
Publication
Path-specific Objectives for Safer Agent Incentives
Paper
Publication
How RL Agents Behave when their Actions are Modified
Paper
Publication
Agent Incentives: A Causal Perspective
Paper
Publication
Solving Common-Payoff Games with Approximate Policy Iteration
Paper
Publication
Relative Variational Intrinsic Control
Paper
Publication
Options of Interest: Temporal Abstraction with Interest Functions
Paper
Publication
Policy-Guided Heuristic Search with Guarantees
Paper
Publication
Gamma-Nets: Generalizing Value Estimation over Timescale
Paper
Publication
Deep Q-learning from Demonstrations
Paper
Publication
Increasing the Action Gap: New Operators for Reinforcement Learning
Paper
Publication
Deep Reinforcement Learning with Double Q-learning
Paper
Publication
Compress and Control
Paper
Publication
Fast gradient descent for drifting least squares regression, with application to bandits