
Quinoa: a Qfunction You Infer Normalized Over Actions
We present an algorithm for learning an approximate actionvalue soft Q...
read it

ContinuousDiscrete Reinforcement Learning for Hybrid Control in Robotics
Many realworld control problems involve both discrete decision variable...
read it

Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
Offpolicy reinforcement learning algorithms promise to be applicable in...
read it

Imagined Value Gradients: ModelBased Policy Optimization with Transferable Latent Dynamics Models
Humans are masters at quickly learning many complex tasks, relying on an...
read it

Graph networks as learnable physics engines for inference and control
Understanding and interacting with everyday physical scenes requires ric...
read it

Relative Entropy Regularized Policy Iteration
We present an offpolicy actorcritic algorithm for Reinforcement Learni...
read it

Simultaneously Learning Vision and Featurebased Control Policies for Realworld BallinaCup
We present a method for fast training of vision based control policies o...
read it

Simple Sensor Intentions for Exploration
Modern reinforcement learning algorithms can learn solutions to increasi...
read it

Regularized Hierarchical Policies for Compositional Transfer in Robotics
The successful application of flexible, general learning algorithms  s...
read it

Playing Atari with Deep Reinforcement Learning
We present the first deep learning model to successfully learn control p...
read it

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
We propose a general and modelfree approach for Reinforcement Learning ...
read it

Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex be...
read it

Learning and Transfer of Modulated Locomotor Controllers
We study a novel architecture and training procedure for locomotion task...
read it

PVEs: PositionVelocity Encoders for Unsupervised Learning of Structured State Representations
We propose positionvelocity encoders (PVEs) which learnwithout super...
read it

Improving Deep Neural Networks with Probabilistic Maxout Units
We present a probabilistic variant of the recently introduced maxout uni...
read it

Multimodal Deep Learning for Robust RGBD Object Recognition
Robust object recognition is a crucial ingredient of many, if not all, r...
read it

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
We introduce Embed to Control (E2C), a method for model learning and con...
read it

Striving for Simplicity: The All Convolutional Net
Most modern convolutional neural networks (CNNs) used for object recogni...
read it

Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
Deep convolutional networks have proven to be very successful in learnin...
read it

DeepMind Control Suite
The DeepMind Control Suite is a set of continuous control tasks with a s...
read it

Learning by Playing  Solving Sparse Reward Tasks from Scratch
We propose Scheduled Auxiliary Control (SACX), a new learning paradigm ...
read it

Maximum a Posteriori Policy Optimisation
We introduce a new algorithm for reinforcement learning called Maximum a...
read it

Selfsupervised Learning of Image Embedding for Continuous Control
Operating directly from raw high dimensional sensory inputs like images ...
read it

Robust Reinforcement Learning for Continuous Control with Model Misspecification
We provide a framework for incorporating robustness  to perturbations ...
read it

VMPO: OnPolicy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Some of the most successful applications of deep reinforcement learning ...
read it

A Distributional View on MultiObjective Policy Optimization
Many realworld problems require trading off multiple competing objectiv...
read it
Martin Riedmiller
verfied profile
Research Scientist at Google DeepMind