DeepAI AI Chat
Log In Sign Up

Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences

by   Daniel S. Brown, et al.

Bayesian reward learning from demonstrations enables rigorous safety and uncertainty analysis when performing imitation learning. However, Bayesian reward learning methods are typically computationally intractable for complex control problems. We propose a highly efficient Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by first pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference. We evaluate our proposed approach on the task of learning to play Atari games from demonstrations, without access to the game score. For Atari games our approach enables us to generate 100,000 samples from the posterior over reward functions in only 5 minutes using a personal laptop. Furthermore, our proposed approach achieves comparable or better imitation learning performance than state-of-the-art methods that only find a point estimate of the reward function. Finally, we show that our approach enables efficient high-confidence policy performance bounds. We show that these high-confidence performance bounds can be used to rank the performance and risk of a variety of evaluation policies, despite not having samples of the reward function. We also show evidence that high-confidence performance bounds can be used to detect reward hacking in complex imitation learning problems.


page 5

page 15

page 16


Deep Bayesian Reward Learning from Preferences

Bayesian inverse reinforcement learning (IRL) methods are ideal for safe...

PAGAR: Imitation Learning with Protagonist Antagonist Guided Adversarial Reward

Imitation learning (IL) algorithms often rely on inverse reinforcement l...

Few-Shot Bayesian Imitation Learning with Logic over Programs

We describe an expressive class of policies that can be efficiently lear...

Policy Gradient Bayesian Robust Optimization for Imitation Learning

The difficulty in specifying rewards for many real-world problems has le...

Genetic Imitation Learning by Reward Extrapolation

Imitation learning demonstrates remarkable performance in various domain...

A Ranking Game for Imitation Learning

We propose a new framework for imitation learning - treating imitation a...

Bayesian Learning for Dynamic Inference

The traditional statistical inference is static, in the sense that the e...