Bayesian Policy Reuse

by   Benjamin Rosman, et al.

A long-lived autonomous agent should be able to respond online to novel instances of tasks from a familiar domain. Acting online requires 'fast' responses, in terms of rapid convergence, especially when the task instance has a short duration, such as in applications involving interactions with humans. These requirements can be problematic for many established methods for learning to act. In domains where the agent knows that the task instance is drawn from a family of related tasks, albeit without access to the label of any given instance, it can choose to act through a process of policy reuse from a library, rather than policy learning from scratch. In policy reuse, the agent has prior knowledge of the class of tasks in the form of a library of policies that were learnt from sample task instances during an offline training phase. We formalise the problem of policy reuse, and present an algorithm for efficiently responding to a novel task instance by reusing a policy from the library of existing policies, where the choice is based on observed 'signals' which correlate to policy performance. We achieve this by posing the problem as a Bayesian choice problem with a corresponding notion of an optimal response, but the computation of that response is in many cases intractable. Therefore, to reduce the computation cost of the posterior, we follow a Bayesian optimisation approach and define a set of policy selection functions, which balance exploration in the policy library against exploitation of previously tried policies, together with a model of expected performance of the policy library on their corresponding task instances. We validate our method in several simulated domains of interactive, short-duration episodic tasks, showing rapid convergence in unknown task variations.


page 21

page 25


Lifetime policy reuse and the importance of task capacity

A long-standing challenge in artificial intelligence is lifelong learnin...

Context-Aware Policy Reuse

Transfer learning can greatly speed up reinforcement learning for a new ...

CUP: Critic-Guided Policy Reuse

The ability to reuse previous policies is an important aspect of human i...

Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning

Bayesian policy reuse (BPR) is a general policy transfer framework for s...

On the Value of Myopic Behavior in Policy Reuse

Leveraging learned strategies in unfamiliar scenarios is fundamental to ...

FIRL: Fast Imitation and Policy Reuse Learning

Intelligent robotics policies have been widely researched for challengin...

DreamDecompiler: Improved Bayesian Program Learning by Decompiling Amortised Knowledge

Solving program induction problems requires searching through an enormou...

Please sign up or login with your details

Forgot password? Click here to reset