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.

First, the agent engages in unsupervised pre-training during which it is encouraged to visit a diverse set of states so its queries can provide more meaningful signal than on randomly collected experience (left). Then, a teacher provides preferences between two clips of behavior, and we learn a reward model based on them. The agent is updated to maximize the expected return under the model. We also relabel all its past experiences with this model to maximize their utilization to update the policy (right).

Novel Behaviors

We demonstrate that PEBBLE can learn behaviors for which a typical reward function is difficult to engineer very efficiently.

Comparison to Prior Work

We compare our approach to prior methods in learning a variety complex continuous control tasks without being able to directly observe the ground truth reward function. Specifically, we consider learning locomotion skills as well as robotic manipulation.

Learning curves on locomotion tasks as measured on the ground truth reward. The solid line and shaded regions represent the mean and standard deviation, respectively, across ten runs. Asymptotic performance of PPO and Preference PPO is indicated by dotted lines of the corresponding color.

Learning curves on robotic manipulation tasks as measured on the success rate. The solid line and shaded regions represent the mean and standard deviation, respectively, across ten runs. Asymptotic performance of PPO and Preference PPO is indicated by dotted lines of the corresponding color.