Related papers: Curiosity-Driven Reinforcement Learning based Low-…

This paper proposes a robust control design method using reinforcement-learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement-learning algorithm with a new…

We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming and noisy data only from a single and ongoing trial. It accomplishes such…

We first define appropriate state representation and action space, and then design an adjustment mechanism based on the actions selected by the intelligent agent. The adjustment mechanism outputs the next state and reward value of the…

Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose…

Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action…

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

Model-based reinforcement learning (MBRL) with real-time planning has shown great potential in locomotion and manipulation control tasks. However, the existing planning methods, such as the Cross-Entropy Method (CEM), do not scale well to…

We present a rational analysis of curiosity, proposing that people's curiosity is driven by seeking stimuli that maximize their ability to make appropriate responses in the future. This perspective offers a way to unify previous theories of…

Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive…

Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot…

This work in the field of developmental cognitive robotics aims to devise a new domain bridging between reinforcement learning and imitation learning, with a model of the intrinsic motivation for learning agents to learn with guidance from…

When learning to ride a bike, a child falls down a number of times before achieving the first success. As falling down usually has only mild consequences, it can be seen as a tolerable failure in exchange for a faster learning process, as…

The contribution focuses on the problem of exploration within the task of knowledge transfer. Knowledge transfer refers to the useful application of the knowledge gained while learning the source task in the target task. The intended…

Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion. In this work, we leverage surprise from mismatches in touch feedback…

While learning by teaching is a popular pedagogical technique, it is a learning phenomenon that is difficult to study due to variability in the tutor-tutee pairings and learning environments. In this paper, we introduce the Curiosity…

We propose a novel text generation task, namely Curiosity-driven Question Generation. We start from the observation that the Question Generation task has traditionally been considered as the dual problem of Question Answering, hence…

A learning algorithm based on primary school teaching and learning is presented. The methodology is to continuously evaluate a student and to give them training on the examples for which they repeatedly fail, until, they can correctly…

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Guided policy search algorithms have been proven to work with incredible accuracy for not only controlling a complicated dynamical system, but also learning optimal policies from various unseen instances. One assumes true nature of the…