Related papers: Learning Task-Driven Control Policies via Informat…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and…
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…
Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain.…
A properly designed controller can help improve the quality of experimental measurements or force a dynamical system to follow a completely new time-evolution path. Recent developments in deep reinforcement learning have made steep advances…
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…
In this work we investigate and demonstrate benefits of a Bayesian approach to imitation learning from multiple sensor inputs, as applied to the task of opening office doors with a mobile manipulator. Augmenting policies with additional…
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…
In multi-agent deep reinforcement learning, extracting sufficient and compact information of other agents is critical to attain efficient convergence and scalability of an algorithm. In canonical frameworks, distilling of such information…
Deep reinforcement learning (DRL) agents are often sensitive to visual changes that were unseen in their training environments. To address this problem, we leverage the sequential nature of RL to learn robust representations that encode…
Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires…
Batch reinforcement learning enables policy learning without direct interaction with the environment during training, relying exclusively on previously collected sets of interactions. This approach is, therefore, well-suited for high-risk…
Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end…
Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…
Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneously within dynamic environments. We apply deep reinforcement learning (DRL) to learn a decentralized end-to-end policy which maps raw…
Policy learning focuses on devising strategies for agents in embodied artificial intelligence systems to perform optimal actions based on their perceived states. One of the key challenges in policy learning involves handling complex,…
Designing a stabilizing controller for nonlinear systems is a challenging task, especially for high-dimensional problems with unknown dynamics. Traditional reinforcement learning algorithms applied to stabilization tasks tend to drive the…
In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…
Data-efficient reinforcement learning (RL) in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. We consider a particularly important instance of this…
This paper presents an approach for data-driven policy refinement in reinforcement learning, specifically designed for safety-critical applications. Our methodology leverages the strengths of data-driven optimization and reinforcement…
Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are…