Recently, visual representation learning has been shown to be effective and promising for boosting sample efficiency in RL.
On a high-end machine, EnvPool achieves 1 million frames per second for the environment execution on Atari environments and 3 million frames per second on MuJoCo environments.
With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks.
no code implementations • 25 Aug 2021 • Austin Derrow-Pinion, Jennifer She, David Wong, Oliver Lange, Todd Hester, Luis Perez, Marc Nunkesser, Seongjae Lee, Xueying Guo, Brett Wiltshire, Peter W. Battaglia, Vishal Gupta, Ang Li, Zhongwen Xu, Alvaro Sanchez-Gonzalez, Yujia Li, Petar Veličković
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike.
In this paper, we extend the use of emphatic methods to deep reinforcement learning agents.
Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster.
Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints.
Automating the discovery of update rules from data could lead to more efficient algorithms, or algorithms that are better adapted to specific environments.
In this work, we propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network, solely from interactive experience with its environment.
Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well on a new domain.
Furthermore, we show that unlike policy transfer methods that capture "how" the agent should behave, the learned reward functions can generalise to other kinds of agents and to changes in the dynamics of the environment by capturing "what" the agent should strive to do.
Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this departs from the focus in much of machine learning on agents learning answers to externally defined questions.
Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output.
We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i. e., referring expression.
Then, we demonstrate that with our model, machine-labeled image annotations are very effective and abundant resources to perform object recognition on novel categories.
no code implementations • 17 Jun 2016 • Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
In this work, we introduce Video Question Answering in temporal domain to infer the past, describe the present and predict the future.
In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos.
In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available.
We address the challenging problem of utilizing related exemplars for complex event detection while multiple features are available.
Compared to complex event videos, these external videos contain simple contents such as objects, scenes and actions which are the basic elements of complex events.