research
∙
06/05/2023
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
We propose a new method for count-based exploration in high-dimensional ...
share
research
∙
01/18/2023
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Despite the advancement of machine learning techniques in recent years, ...
research
∙
12/29/2022
On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
Advances in reinforcement learning have led to its successful applicatio...
research
∙
12/29/2022
Effects of Data Geometry in Early Deep Learning
Deep neural networks can approximate functions on different types of dat...
research
∙
11/26/2022
Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex
AlphaZero, an approach to reinforcement learning that couples neural net...
research
∙
10/20/2022
Model-based Lifelong Reinforcement Learning with Bayesian Exploration
We propose a model-based lifelong reinforcement-learning approach that e...
research
∙
09/28/2022
Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
Dynamic movement primitives are widely used for learning skills which ca...
research
∙
08/12/2022
RLang: A Declarative Language for Expression Prior Knowledge for Reinforcement Learning
Communicating useful background knowledge to reinforcement learning (RL)...
research
∙
06/07/2022
Meta-Learning Transferable Parameterized Skills
We propose a novel parameterized skill-learning algorithm that aims to l...
research
∙
05/11/2022
Characterizing the Action-Generalization Gap in Deep Q-Learning
We study the action generalization ability of deep Q-learning in discret...
research
∙
05/04/2022
Learning Abstract and Transferable Representations for Planning
We are concerned with the question of how an agent can acquire its own r...
research
∙
04/22/2022
Adaptive Online Value Function Approximation with Wavelets
Using function approximation to represent a value function is necessary ...
research
∙
04/18/2022
Automatic Encoding and Repair of Reactive High-Level Tasks with Learned Abstract Representations
We present a framework that, given a set of skills a robot can perform, ...
research
∙
03/20/2022
Hierarchical Reinforcement Learning of Locomotion Policies in Response to Approaching Objects: A Preliminary Study
Animals such as rabbits and birds can instantly generate locomotion beha...
research
∙
11/17/2021
IKFlow: Generating Diverse Inverse Kinematics Solutions
Inverse kinematics - finding joint poses that reach a given Cartesian-sp...
research
∙
10/23/2021
Guided Policy Search for Parameterized Skills using Adverbs
We present a method for using adverb phrases to adjust skill parameters ...
research
∙
10/23/2021
Coarse-Grained Smoothness for RL in Metric Spaces
Principled decision-making in continuous state–action spaces is impossib...
research
∙
10/19/2021
Towards Optimal Correlational Object Search
In realistic applications of object search, robots will need to locate t...
research
∙
10/15/2021
Learning to Infer Kinematic Hierarchies for Novel Object Instances
Manipulating an articulated object requires perceiving itskinematic hier...
research
∙
10/11/2021
Generalizing to New Domains by Mapping Natural Language to Lifted LTL
Recent work on using natural language to specify commands to robots has ...
research
∙
09/24/2021
RMPs for Safe Impedance Control in Contact-Rich Manipulation
Variable impedance control in operation-space is a promising approach to...
research
∙
08/12/2021
HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning
Sparse rewards and long time horizons remain challenging for reinforceme...
research
∙
07/28/2021
Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings
Learning continuous control in high-dimensional sparse reward settings, ...
research
∙
06/08/2021
Learning Markov State Abstractions for Deep Reinforcement Learning
The fundamental assumption of reinforcement learning in Markov decision ...
research
∙
06/07/2021
Learning to Detect Multi-Modal Grasps for Dexterous Grasping in Dense Clutter
Grasping arbitrary objects in densely cluttered novel environments is a ...
research
∙
01/12/2021
Bootstrapping Motor Skill Learning with Motion Planning
Learning a robot motor skill from scratch is impractically slow; so much...
research
∙
10/17/2020
Task Scoping: Building Goal-Specific Abstractions for Planning in Complex Domains
A generally intelligent agent requires an open-scope world model: one ri...
research
∙
06/04/2020
Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion
We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO...
research
∙
05/06/2020
Multi-Resolution POMDP Planning for Multi-Object Search in 3D
Robots operating in household environments must find objects on shelves,...
research
∙
04/28/2020
Finding Macro-Actions with Disentangled Effects for Efficient Planning with the Goal-Count Heuristic
The difficulty of classical planning increases exponentially with search...
research
∙
10/23/2019
Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control
Robots need to learn skills that can not only generalize across similar ...
research
∙
07/06/2019
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
A key challenge in intelligent robotics is creating robots that are capa...
research
∙
05/30/2019
Grounding Language Attributes to Objects using Bayesian Eigenobjects
We develop a system to disambiguate objects based on simple physical des...
research
∙
05/28/2019
Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priors
We introduce a new method for category-level pose estimation which produ...
research
∙
05/28/2019
Learning Portable Representations for High-Level Planning
We present a framework for autonomously learning a portable representati...
research
∙
03/02/2019
Discovering Options for Exploration by Minimizing Cover Time
One of the main challenges in reinforcement learning is solving tasks wi...
research
∙
10/16/2018
Finding Options that Minimize Planning Time
While adding temporally abstract actions, or options, to an agent's acti...
research
∙
07/23/2018
Scanning the Internet for ROS: A View of Security in Robotics Research
Because robots can directly perceive and affect the physical world, secu...
research
∙
06/20/2018
Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision
We introduce Hybrid Bayesian Eigenobjects (HBEOs), a novel representatio...
research
∙
09/05/2017
Active Exploration for Learning Symbolic Representations
We introduce an online active exploration algorithm for data-efficiently...
research
∙
09/01/2017
Mean Actor Critic
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action...
research
∙
08/11/2017
Communicating Robot Arm Motion Intent Through Mixed Reality Head-mounted Displays
Efficient motion intent communication is necessary for safe and collabor...
research
∙
06/20/2017
Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes
We introduce a new formulation of the Hidden Parameter Markov Decision P...
research
∙
12/01/2016
Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes
Due to physiological variation, patients diagnosed with the same conditi...
research
∙
09/25/2015
Constructing Abstraction Hierarchies Using a Skill-Symbol Loop
We describe a framework for building abstraction hierarchies whereby an ...
research
∙
09/05/2015
Reinforcement Learning with Parameterized Actions
We introduce a model-free algorithm for learning in Markov decision proc...
research
∙
08/15/2013
Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations
Control applications often feature tasks with similar, but not identical...
research
∙
06/27/2012