30 citations · 76 across the 4 of their papers we have counts for
6 papers · 1 filter
Value Alignment Verification
Daniel S. Brown, Jordan Schneider, Anca D. Dragan +1
As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent's performance an…
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Daniel S. Brown, Russell Coleman, Ravi Srinivasan +1
Bayesian reward learning from demonstrations enables rigorous safety and uncertainty analysis when performing imitation learning. However, Bayesian reward learning methods are typi…
Deep Bayesian Reward Learning from Preferences
Daniel S. Brown, Scott Niekum
Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a l…
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan +1
A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a rewa…
Risk-Aware Active Inverse Reinforcement Learning
Daniel S. Brown, Yuchen Cui, Scott Niekum
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query s…
Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications
Daniel S. Brown, Scott Niekum
Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL,…