Reinforcement Learning

Bayesian Policy Reuse
A long-lived autonomous agent should be able to respond online to novel instances of tasks from a familiar domain. Acting online …
PDF Cite
Identifying and Tracking Switching, Non-stationary Opponents: a Bayesian Approach
In many situations, agents are required to use a set of strategies (behaviors) and switch among them during the course of an …
PDF Cite
Reinforcement Learning with Parameterized Actions
We introduce a model-free algorithm for learning in Markov decision processes with parameterized actions—discrete actions with …
PDF Cite
Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning
We present a method for segmenting a set of unstructured demonstration trajectories to discover reusable skills using inverse …
PDF Cite Project
Enhancing Agent Safety through Autonomous Environment Adaptation
Exploration and self-directed learning are valuable components of early childhood development. This often comes at an unacceptable …
PDF Cite
Action Priors for Learning Domain Invariances
An agent tasked with solving a number of different decision making problems in similar environments has an opportunity to learn over a …
PDF Cite
Context-based Online Policy Instantiation for Multiple Tasks and Changing Environments
This paper addresses the problem of online decision making in continually changing and complex environments, with inherent …
PDF Cite
Behavioural Domain Knowledge Transfer for Autonomous Agents
An agent continuously performing different tasks in the same domain has the opportunity to learn, over the course of its operational …
PDF Cite
Feature Selection for Domain Knowledge Representation through Multitask Learning
Representation learning is a difficult and important problem for autonomous agents. This paper presents an approach to automatic …
PDF Cite
Adapting Interaction Environments to Diverse Users through Online Action Set Selection
Interactive interfaces are a common feature of many systems ranging from field robotics to video games. In most applications, these …
PDF Cite