Related papers: An Open-Source Multi-Goal Reinforcement Learning E…
In recent years, fully differentiable rigid body physics simulators have been developed, which can be used to simulate a wide range of robotic systems. In the context of reinforcement learning for control, these simulators theoretically…
Deep Reinforcement Learning (DRL) has shown its promising capabilities to learn optimal policies directly from trial and error. However, learning can be hindered if the goal of the learning, defined by the reward function, is "not optimal".…
In real-world human-robot systems, it is essential for a robot to comprehend human objectives and respond accordingly while performing an extended series of motor actions. Although human objective alignment has recently emerged as a…
Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…
Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We…
Despite promising progress in reinforcement learning (RL), developing algorithms for autonomous driving (AD) remains challenging: one of the critical issues being the absence of an open-source platform capable of training and effectively…
Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it often struggles to solve tasks that require more temporally extended reasoning. In this work, we propose to incorporate imagined subgoals into…
In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator…
Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on…
In this paper we study how transforming regular reinforcement learning environments into goal-conditioned environments can let agents learn to solve tasks autonomously and reward-free. We show that an agent can learn to solve tasks by…
Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…
Robots have been successfully used to perform tasks with high precision. In real-world environments with sparse rewards and multiple goals, learning is still a major challenge and Reinforcement Learning (RL) algorithms fail to learn good…
In this paper VisualEnv, a new tool for creating visual environment for reinforcement learning is introduced. It is the product of an integration of an open-source modelling and rendering software, Blender, and a python module used to…
Deep reinforcement learning (RL) has recently shown great promise in robotic continuous control tasks. Nevertheless, prior research in this vein center around the centralized learning setting that largely relies on the communication…
Robot motion can have many goals. Depending on the task, we might optimize for pose error, speed, collision, or similarity to a human demonstration. Motivated by this, we present PyRoki: a modular, extensible, and cross-platform toolkit for…
This paper presents Tunnel, a simple, open source, reinforcement learning training environment for high performance aircraft. It integrates the F16 3D nonlinear flight dynamics into OpenAI Gymnasium python package. The template includes…
Using simulation to train robot manipulation policies holds the promise of an almost unlimited amount of training data, generated safely out of harm's way. One of the key challenges of using simulation, to date, has been to bridge the…
The utilization of broad datasets has proven to be crucial for generalization for a wide range of fields. However, how to effectively make use of diverse multi-task data for novel downstream tasks still remains a grand challenge in…
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…
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes…