PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

by   Kimin Lee, et al.

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher's preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent's past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions.


page 5

page 7

page 8

page 15

page 16


Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

Conveying complex objectives to reinforcement learning (RL) agents often...

Few-Shot Preference Learning for Human-in-the-Loop RL

While reinforcement learning (RL) has become a more popular approach for...

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

Exploration and reward specification are fundamental and intertwined cha...

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Reinforcement learning provides a general framework for flexible decisio...

Interactive Learning from Activity Description

We present a novel interactive learning protocol that enables training r...

Learning What To Do by Simulating the Past

Since reward functions are hard to specify, recent work has focused on l...

Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores

Interactive reinforcement learning has shown promise in learning complex...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset