PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
This addresses the challenge of leveraging varied, unlabeled demonstrations in multi-agent settings like autonomous driving, offering a novel integration method for improved learning.
The paper tackles the problem of reinforcement learning with no-reward demonstrations by proposing PsiPhi-learning, which integrates inverse temporal difference learning with successor features to learn from diverse agent data without reward labels, achieving improvements in RL, IRL, imitation, and few-shot transfer with derived worst-case bounds for zero-shot transfer.
We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or goals of these agents, and their objectives and levels of expertise may vary widely. These assumptions are common in multi-agent settings, such as autonomous driving. To effectively use this data, we turn to the framework of successor features. This allows us to disentangle shared features and dynamics of the environment from agent-specific rewards and policies. We propose a multi-task inverse reinforcement learning (IRL) algorithm, called \emph{inverse temporal difference learning} (ITD), that learns shared state features, alongside per-agent successor features and preference vectors, purely from demonstrations without reward labels. We further show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $ΨΦ$-learning (pronounced `Sci-Fi'). We provide empirical evidence for the effectiveness of $ΨΦ$-learning as a method for improving RL, IRL, imitation, and few-shot transfer, and derive worst-case bounds for its performance in zero-shot transfer to new tasks.