Search Results for author:
Found 12 papers, 7 papers with code
Tracr: Compiled Transformers as a Laboratory for Interpretability
Interpretability research aims to build tools for understanding machine learning (ML) models.
Red-Teaming the Stable Diffusion Safety Filter
We then reverse-engineer the filter and find that while it aims to prevent sexual content, it ignores violence, gore, and other similarly disturbing content.
Active Exploration for Inverse Reinforcement Learning
We propose a novel IRL algorithm: Active exploration for Inverse Reinforcement Learning (AceIRL), which actively explores an unknown environment and expert policy to quickly learn the expert's reward function and identify a good policy.
Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning
Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide.
Interactively Learning Preference Constraints in Linear Bandits
We provide an instance-dependent lower bound for constrained linear best-arm identification and show that ACOL's sample complexity matches the lower bound in the worst-case.
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
Addressing the Long-term Impact of ML Decisions via Policy Regret
To capture the long-term effects of ML-based allocation decisions, we study a setting in which the reward from each arm evolves every time the decision-maker pulls that arm.
Learning What To Do by Simulating the Past
Since reward functions are hard to specify, recent work has focused on learning policies from human feedback.
Information Directed Reward Learning for Reinforcement Learning
For many reinforcement learning (RL) applications, specifying a reward is difficult.
Challenges for Using Impact Regularizers to Avoid Negative Side Effects
Finally, we explore promising directions to overcome the unsolved challenges in preventing negative side effects with impact regularizers.
Detecting Spiky Corruption in Markov Decision Processes
We show that if the reward corruption in a CRMDP is sufficiently "spiky", the environment is solvable.
Sensing Social Media Signals for Cryptocurrency News
The ability to track and monitor relevant and important news in real-time is of crucial interest in multiple industrial sectors.
