Search Results for author:
Found 11 papers, 8 papers with code
A StrongREJECT for Empty Jailbreaks
We show that our new grading scheme better accords with human judgment of response quality and overall jailbreak effectiveness, especially on the sort of low-quality responses that contribute the most to over-estimation of jailbreak performance on existing benchmarks.
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Our benchmark results show that many models are vulnerable to the attack strategies in the Tensor Trust dataset.
imitation: Clean Imitation Learning Implementations
imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch.
An Empirical Investigation of Representation Learning for Imitation
We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation across several environment suites.
A Primer on Maximum Causal Entropy Inverse Reinforcement Learning
Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment.
DERAIL: Diagnostic Environments for Reward And Imitation Learning
We evaluate a range of common reward and imitation learning algorithms on our tasks.
The MAGICAL Benchmark for Robust Imitation
This rewards precise reproduction of demonstrations in one particular environment, but provides little information about how robustly an algorithm can generalise the demonstrator's intent to substantially different deployment settings.
ASNets: Deep Learning for Generalised Planning
In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets).
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
By enforcing a constraint on the mutual information between the observations and the discriminator's internal representation, we can effectively modulate the discriminator's accuracy and maintain useful and informative gradients.
Action Schema Networks: Generalised Policies with Deep Learning
In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems.
Human Pose Forecasting via Deep Markov Models
Human pose forecasting is an important problem in computer vision with applications to human-robot interaction, visual surveillance, and autonomous driving.
