Add to ORKGInternational audienceAimed at on-board robot training, an approach hybridizing active preference learning and reinforcement learning is presented: Interactive Bayesian Policy Search (IBPS) builds a robotic controller through direct and frugal interaction with the human expert, iteratively emitting preferences among a few behaviors demonstrated by the robot. These preferences allow the robot to gradually refine its policy utility estimate, and select a new policy to be demonstrated, after an Expected Utility of Selection criterion. The paper contribution is on handling the preference noise, due to expert's mistakes or disinterest when demonstrated behaviors are equally unsatisfactory. A noise model is proposed, enabling a resource-limited r...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract—This paper proposes a high-level Reinforcement Learning (RL) control system for solving the...
International audienceAimed at on-board robot training, an approach hybridizing active preference le...
This work tackles in-situ robotics: the goal is to learn a policy while the robot operates in the re...
International audienceMany machine learning approaches in robotics, based on re- inforcement learnin...
Abstract. Many machine learning approaches in robotics, based on re-inforcement learning, inverse op...
Most policy search (PS) algorithms require thousands of training episodes to find an effective polic...
Most policy search algorithms require thousands of training episodes to find an effective policy, wh...
This thesis studies a central problem in human-robot interaction (HRI): How can non-expert users spe...
International audienceThis paper focuses on reinforcement learning (RL) with limited prior knowledge...
This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partiall...
This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partiall...
As most action generation problems of autonomous robots can be phrased in terms of sequential decisi...
In real-world robotic applications, many factors, both at low-level (e.g., vision and motion control...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract—This paper proposes a high-level Reinforcement Learning (RL) control system for solving the...
International audienceAimed at on-board robot training, an approach hybridizing active preference le...
This work tackles in-situ robotics: the goal is to learn a policy while the robot operates in the re...
International audienceMany machine learning approaches in robotics, based on re- inforcement learnin...
Abstract. Many machine learning approaches in robotics, based on re-inforcement learning, inverse op...
Most policy search (PS) algorithms require thousands of training episodes to find an effective polic...
Most policy search algorithms require thousands of training episodes to find an effective policy, wh...
This thesis studies a central problem in human-robot interaction (HRI): How can non-expert users spe...
International audienceThis paper focuses on reinforcement learning (RL) with limited prior knowledge...
This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partiall...
This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partiall...
As most action generation problems of autonomous robots can be phrased in terms of sequential decisi...
In real-world robotic applications, many factors, both at low-level (e.g., vision and motion control...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract. This paper focuses on reinforcement learning (RL) with lim-ited prior knowledge. In the do...
Abstract—This paper proposes a high-level Reinforcement Learning (RL) control system for solving the...