Home
Projects
Publications
People
Join the Lab
Contact
Login
1
Hierarchical Subtask Discovery with Non-negative Matrix Factorization
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, …
Adam Earle
,
Andrew Saxe
,
Benjamin Rosman
PDF
Cite
Project
Social Cobots: Anticipatory Decision-Making for Collaborative Robots Incorporating Unexpected Human Behaviors
We propose an architecture as a robot’s decision-making mechanism to anticipate a human’s state of mind, and so plan …
Orhan Can Görür
,
Benjamin Rosman
,
Fikret Sivrikaya
,
Sahin Albayrak
PDF
Cite
Belief Reward Shaping in Reinforcement Learning
A key challenge in many reinforcement learning problems is delayed rewards, which can significantly slow down learning. Although reward …
Ofir Marom
,
Benjamin Rosman
PDF
Cite
Supplementary Material
Raw Material Selection for Object Construction
An important step in the construction of novel objects is the ability to recognise combinations of raw materials which are likely to be …
Jason Perlow
,
Benjamin Rosman
,
Bradley Hayes
,
Pravesh Ranchod
PDF
Cite
Tracking Influence between Naïve Bayes Models using Score-Based Structure Learning
Current structure learning practices in Bayesian networks have been developed to learn the structure between observable variables and …
Ritesh Ajoodha
,
Benjamin Rosman
PDF
Cite
Fingerprint Minutiae Extraction using Deep Learning
The high variability of fingerprint data (owing to, e.g., differences in quality, moisture conditions, and scanners) makes the task of …
Luke Darlow
,
Benjamin Rosman
PDF
Cite
Online Constrained Model-based Reinforcement Learning
Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle …
Benjamin van Niekerk
,
Andreas Damianou
,
Benjamin Rosman
PDF
Cite
Hierarchy Through Composition with Multitask LMDPs
Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks …
Andrew Saxe
,
Adam Earle
,
Benjamin Rosman
PDF
Cite
Project
Supplementary Material
An Analysis of Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years. Despite …
Steven James
,
George Konidaris
,
Benjamin Rosman
PDF
Cite
Trajectory Learning from Human Demonstrations via Manifold Mapping
This work proposes a framework that enables arbitrary robots with unknown kinematics models to imitate human demonstrations to acquire …
Michihisa Hiratsuka
,
Ndivhuwo Makondo
,
Benjamin Rosman
,
Osamu Hasegawa
PDF
Cite
«
»
Cite
×