Related papers: Leveraging Sequentiality in Reinforcement Learning…
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…
Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because…
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to…
Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic…
Deep reinforcement learning (DRL) has been proven to be a powerful paradigm for learning complex control policy autonomously. Numerous recent applications of DRL in robotic grasping have successfully trained DRL robotic agents end-to-end,…
In this work, we focus on a robotic unloading problem from visual observations, where robots are required to autonomously unload stacks of parcels using RGB-D images as their primary input source. While supervised and imitation learning…
Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by…
Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large…
Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…
There is a growing interest in learning a velocity command tracking controller of quadruped robot using reinforcement learning due to its robustness and scalability. However, a single policy, trained end-to-end, usually shows a single gait…
Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation…
Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervised loss functions for stably training deep reinforcement…
We present a deep reinforcement learning (deep RL) algorithm that consists of learning-based motion planning and imitation to tackle challenging control problems. Deep RL has been an effective tool for solving many high-dimensional…
Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…
Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which…
In the training process of Deep Reinforcement Learning (DRL), agents require repetitive interactions with the environment. With an increase in training volume and model complexity, it is still a challenging problem to enhance data…
When facing the problem of autonomously learning multiple tasks with reinforcement learning systems, researchers typically focus on solutions where just one parametrised policy per task is sufficient to solve them. However, in complex…
Reinforcement learning for multi-goal robot manipulation tasks poses significant challenges due to the diversity and complexity of the goal space. Techniques such as Hindsight Experience Replay (HER) have been introduced to improve learning…
Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because…
Deep Reinforcement Learning (RL) has emerged as a powerful method for addressing complex control problems, particularly those involving underactuated robotic systems. However, in some cases, policies may require refinement to achieve…