Related papers: Cascade Attribute Network: Decomposing Reinforceme…
We propose the cascade attribute learning network (CALNet), which can learn attributes in a control task separately and assemble them together. Our contribution is twofold: first we propose attribute learning in reinforcement learning (RL).…
At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce…
This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints. Despite its success in many domains, reinforcement learning is challenging to apply to problems with hard constraints,…
Deep reinforcement learning has been applied to solve a variety of control problems in isolation. However, the learned latent representations cannot be optimally reused for other analogous tasks and/or control systems without additional…
This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The…
Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value…
While the recent advances in deep reinforcement learning have achieved impressive results in learning motor skills, many of the trained policies are only capable within a limited set of initial states. We propose a technique to break down a…
A critical problem with the practical utility of controllers trained with deep Reinforcement Learning (RL) is the notable lack of smoothness in the actions learned by the RL policies. This trend often presents itself in the form of control…
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined…
Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…
Control Barrier Functions (CBFs) have emerged as a prominent approach to designing safe navigation systems of robots. Despite their popularity, current CBF-based methods exhibit some limitations: optimization-based safe control techniques…
Behavior Trees are commonly used to model agents for robotics and games, where constrained behaviors must be designed by human experts in order to guarantee that these agents will execute a specific chain of actions given a specific set of…
Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a…
For robotic vehicles to navigate robustly and safely in unseen environments, it is crucial to decide the most suitable navigation policy. However, most existing deep reinforcement learning based navigation policies are trained with a…
Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value…
Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data…
Over the past decade, remarkable progress has been made in adopting deep neural networks to enhance the performance of conventional reinforcement learning. A notable milestone was the development of Deep Q-Networks (DQN), which achieved…
Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant features using feature selection, an algorithm can be given…
Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a large number of options or skills, which can potentially be…