research
∙
06/17/2021
Learning from Demonstration without Demonstrations
State-of-the-art reinforcement learning (RL) algorithms suffer from high...
share
research
∙
04/21/2020
Clustering volatility regimes for dynamic trading strategies
We develop a new method to find the number of volatility regimes in a no...
research
∙
01/20/2020
Reinforcement Learning with Probabilistically Complete Exploration
Balancing exploration and exploitation remains a key challenge in reinfo...
research
∙
09/25/2019
OCTNet: Trajectory Generation in New Environments from Past Experiences
Being able to safely operate for extended periods of time in dynamic env...
research
∙
09/08/2019
Local Sampling-based Planning with Sequential Bayesian Updates
Sampling-based planners are the predominant motion planning paradigm for...
research
∙
10/08/2018
Balancing Global Exploration and Local-connectivity Exploitation with Rapidly-exploring Random disjointed-Trees
Sampling efficiency in a highly constrained environment has long been a ...
research
∙
05/03/2018