Related papers: Automated Curriculum Design for High-dimensional H…

We introduce the problem of curriculum discovery and describe a curriculum learning framework capable of discovering effective curricula in a curriculum space based on prior knowledge about sample difficulty. Using annotation entropy and…

Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learning speed. This paper…

Learning control policies for multi-robot systems (MRS) remains a major challenge due to long-term coordination and the difficulty of obtaining realistic training data. In this work, we address both limitations within an imitation learning…

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic…

In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic…

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained…

There have been numerous attempts in explaining the general learning behaviours by various cognitive models. Multiple hypotheses have been put further to qualitatively argue the best-fit model for motor skill acquisition task and its…

Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems. The field recently experienced growth by successfully adapting architectures…

Enabling a high-degree-of-freedom robot to learn specific skills is a challenging task due to the complexity of robotic dynamics. Reinforcement learning (RL) has emerged as a promising solution; however, addressing such problems requires…

We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train…

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

The learning rate is one of the most important hyper-parameters for model training and generalization. However, current hand-designed parametric learning rate schedules offer limited flexibility and the predefined schedule may not match the…

Robotic assembly tasks involve complex and low-clearance insertion trajectories with varying contact forces at different stages. While the nominal motion trajectory can be easily obtained from human demonstrations through kinesthetic…

Deep reinforcement learning has been recognized as an efficient technique to design optimal strategies for different complex systems without prior knowledge of the control landscape. To achieve a fast and precise control for quantum…

In recent years, a myriad of advanced results have been reported in the community of imitation learning, ranging from parametric to non-parametric, probabilistic to non-probabilistic and Bayesian to frequentist approaches. Meanwhile, ample…

This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and…

Autonomous robotic wiping is an important task in various industries, ranging from industrial manufacturing to sanitization in healthcare. Deep reinforcement learning (Deep RL) has emerged as a promising algorithm, however, it often suffers…

This study investigates how adequate coordination among the different cognitive processes of a humanoid robot can be developed through end-to-end learning of direct perception of visuomotor stream. We propose a deep dynamic neural network…

User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations. Existing approaches focus on single learning experiences and do not…

Dexterous manipulation tasks usually have multiple objectives, and the priorities of these objectives may vary at different phases of a manipulation task. Varying priority makes a robot hardly or even failed to learn an optimal policy with…