Skip to search formSkip to main contentSkip to account menu

Human-level control through deep reinforcement learning

This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
View on Nature (opens in a new tab)

Playing Atari with Deep Reinforcement Learning

This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
View PDF on arXiv (opens in a new tab)

Deterministic Policy Gradient Algorithms

This paper introduces an off-policy actor-critic algorithm that learns a deterministic target policy from an exploratory behaviour policy and demonstrates that deterministic policy gradient algorithms can significantly outperform their stochastic counterparts in high-dimensional action spaces.
View Paper (opens in a new tab)

Striving for Simplicity: The All Convolutional Net

It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.
View PDF on arXiv (opens in a new tab)

A direct adaptive method for faster backpropagation learning: the RPROP algorithm

A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed that performs a local adaptation of the weight-updates according to the behavior of the error function to overcome the inherent disadvantages of pure gradient-descent.
View on IEEE (opens in a new tab)

Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method

NFQ, an algorithm for efficient and effective training of a Q-value function represented by a multi-layer perceptron, is introduced and it is shown empirically, that reasonably few interactions with the plant are needed to generate control policies of high quality.
View via Publisher (opens in a new tab)

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

Embed to Control is introduced, a method for model learning and control of non-linear dynamical systems from raw pixel images that is derived directly from an optimal control formulation in latent space and exhibits strong performance on a variety of complex control problems.
View PDF on arXiv (opens in a new tab)

Maximum a Posteriori Policy Optimisation

This work introduces a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective and develops two off-policy algorithms that are competitive with the state-of-the-art in deep reinforcement learning.
View PDF on arXiv (opens in a new tab)

Emergence of Locomotion Behaviours in Rich Environments

This paper explores how a rich environment can help to promote the learning of complex behavior, and finds that this encourages the emergence of robust behaviours that perform well across a suite of tasks.
View PDF on arXiv (opens in a new tab)

Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

While features learned with this approach cannot compete with class specific features from supervised training on a classification task, it is shown that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)