Search Results for author:
Found 12 papers, 8 papers with code
Preventing Reward Hacking with Occupancy Measure Regularization
Thus, we propose regularizing based on the OM divergence between policies instead of AD divergence to prevent reward hacking.
Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping
Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems.
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
Our goal is to explain why deep RL algorithms often perform well in practice, despite using random exploration and much more expressive function classes like neural networks.
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
We prove that standard applications of preference learning, including reinforcement learning from human feedback (RLHF), implicitly aggregate over hidden contexts according to a well-known voting rule called Borda count.
Bridging RL Theory and Practice with the Effective Horizon
Using BRIDGE, we find that prior bounds do not correlate well with when deep RL succeeds vs. fails, but discover a surprising property that does.
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models
However, these models fail when humans exhibit systematic suboptimality, i. e. when their deviations from optimal behavior are not independent, but instead consistent over time.
Uncertain Decisions Facilitate Better Preference Learning
We give the first statistical analysis of IDT, providing conditions necessary to identify these preferences and characterizing the sample complexity -- the number of decisions that must be observed to learn the tradeoff the human is making to a desired precision.
Perceptual Adversarial Robustness: Generalizable Defenses Against Unforeseen Threat Models
We call this threat model the neural perceptual threat model (NPTM); it includes adversarial examples with a bounded neural perceptual distance (a neural network-based approximation of the true perceptual distance) to natural images.
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models
We call this threat model the neural perceptual threat model (NPTM); it includes adversarial examples with a bounded neural perceptual distance (a neural network-based approximation of the true perceptual distance) to natural images.
Playing it Safe: Adversarial Robustness with an Abstain Option
We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples.
Functional Adversarial Attacks
For simplicity, we refer to functional adversarial attacks on image colors as ReColorAdv, which is the main focus of our experiments.
Capture, Learning, and Synthesis of 3D Speaking Styles
To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers.
