Related papers: Transfer Learning Across Simulated Robots With Dif…

Using tactile sensors for manipulation remains one of the most challenging problems in robotics. At the heart of these challenges is generalization: How can we train a tactile-based policy that can manipulate unseen and diverse objects? In…

Reusing large datasets is crucial to scale vision-based robotic manipulators to everyday scenarios due to the high cost of collecting robotic datasets. However, robotic platforms possess varying control schemes, camera viewpoints, kinematic…

Reinforcement learning is considered as a promising direction for driving policy learning. However, training autonomous driving vehicle with reinforcement learning in real environment involves non-affordable trial-and-error. It is more…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

In robotics, gradient-free optimization algorithms (e.g. evolutionary algorithms) are often used only in simulation because they require the evaluation of many candidate solutions. Nevertheless, solutions obtained in simulation often do not…

The ability to transfer in reinforcement learning is key towards building an agent of general artificial intelligence. In this paper, we consider the problem of learning to simultaneously transfer across both environments (ENV) and tasks…

Recent work has demonstrated the ability of deep reinforcement learning (RL) algorithms to learn complex robotic behaviours in simulation, including in the domain of multi-fingered manipulation. However, such models can be challenging to…

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is…

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the…

Robots are required to autonomously respond to changing situations. Imitation learning is a promising candidate for achieving generalization performance, and extensive results have been demonstrated in object manipulation. However,…

Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating…

We present a visual imitation learning framework that enables learning of robot action policies solely based on expert samples without any robot trials. Robot exploration and on-policy trials in a real-world environment could often be…

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that…

Learning controllers for bipedal robots is a challenging problem, often requiring expert knowledge and extensive tuning of parameters that vary in different situations. Recently, deep reinforcement learning has shown promise at…

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…

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…

In recent years, policy learning methods using either reinforcement or imitation have made significant progress. However, both techniques still suffer from being computationally expensive and requiring large amounts of training data. This…

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training…