IROS 2017: Hybrid control trajectory optimization under uncertainty

IROS 2017: Hybrid control trajectory optimization under uncertainty

Trajectory optimization is a fundamental problem in robotics. While optimization of continuous control trajectories is well developed, many applications require both discrete and continuous, i.e….

Read Article →
IJCAI 2017: Contextual CMA-ES

IJCAI 2017: Contextual CMA-ES

Many stochastic search algorithms are designed to optimize a fixed objective function to learn a task, i.e., if the objective function changes slightly, for example,…

Read Article →
JMLR 2017: Non-parametric Policy Search with Limited Information Loss.

JMLR 2017: Non-parametric Policy Search with Limited Information Loss.

Learning complex control policies from non-linear and redundant sensory input is an important challenge for reinforcement learning algorithms. Non-parametric methods that approximate values functions or transition…

Read Article →
ICML 2017: Local Bayesian Optimization

ICML 2017: Local Bayesian Optimization

Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization. To scale to higher dimensional problems,…

Read Article →
GECCO 2017: Deriving and Improving CMA-ES with Information-Geometric Trustregions

GECCO 2017: Deriving and Improving CMA-ES with Information-Geometric Trustregions

CMA-ES is one of the most popular stochastic search algorithms. It performs favourably in many tasks without the need of extensive parameter tuning. The algorithm…

Read Article →
ICAPS 2017: State-regularized policy search for linearized dynamical systems

ICAPS 2017: State-regularized policy search for linearized dynamical systems

Trajectory-Centric Reinforcement Learning and Trajectory Optimization methods optimize a sequence of feedbackcontrollers by taking advantage of local approximations of model dynamics and cost functions. Stability of the policy…

Read Article →
ISER 2016: Experiments with hierarchical reinforcement learning of multiple grasping policies

ISER 2016: Experiments with hierarchical reinforcement learning of multiple grasping policies

Robotic grasping has attracted considerable interest, but it still remains a challenging task. The data-driven approach is a promising solution to the robotic grasping problem; this approach…

Read Article →
ICRA 2017: Empowered Skills

ICRA 2017: Empowered Skills

Robot Reinforcement Learning (RL) algorithms return a policy that maximizes a global cumulative reward signal but typically do not create diverse behaviors. Hence, the policy…

Read Article →
ICRA 2017: Layered Direct Policy Search for Learning Hierarchical Skills

ICRA 2017: Layered Direct Policy Search for Learning Hierarchical Skills

Solutions to real world robotic tasks often require complex behaviors in high dimensional continuous state and action spaces. Reinforcement Learning (RL) is aimed at learning…

Read Article →
ICML 2016: Model-Free Trajectory Optimization for Reinforcement Learning

ICML 2016: Model-Free Trajectory Optimization for Reinforcement Learning

Many of the recent Trajectory Optimization algorithms alternate between local approximation of the dynamics and conservative policy update. However, linearly approximating the dynamics in order to derive…

Read Article →