Reinforcement Learning

Hierarchical Subtask Discovery with Non-negative Matrix Factorization
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, …
PDF Cite Project
Hierarchy Through Composition with Multitask LMDPs
Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks …
PDF Cite Project Supplementary Material
A Bayesian approach for Learning and Tracking Switching, Non-stationary Opponents
In many situations, agents are required to use a set of strategies (behaviors) and switch among them during the course of an …
PDF Cite
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