Bayesian policy reuse
From MaRDI portal
Publication:1689554
Abstract: 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.
Recommendations
- Bayesian Reinforcement Learning with Exploration
- Finding memoryless probabilistic relational policies for inter-task reuse
- Reward-weighted regression with sample reuse for direct policy search in reinforcement learning
- Active contextual policy search
- Autonomous reinforcement learning with experience replay
Cites work
- scientific article; zbMATH DE number 795288 (Why is no real title available?)
- A Structured Multiarmed Bandit Problem and the Greedy Policy
- Asymptotically efficient adaptive allocation rules
- Bayesian policy gradient and actor-critic algorithms
- Computing a classic index for finite-horizon bandits
- Contextual bandits with similarity information
- Finite-time analysis of the multiarmed bandit problem
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
- Transfer learning for reinforcement learning domains: a survey
Cited in
(3)
This page was built for publication: Bayesian policy reuse
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1689554)
