Nicolas Heess

is this you? claim profile

0 followers
Google

PhD student at the Institute for Adaptive and Neural Computation, University of Edinburgh

Counterfactual Credit Assignment in Model-Free Reinforcement Learning

Credit assignment in reinforcement learning is the problem of measuring ...
11/18/2020 ∙ by Thomas Mesnard, et al. ∙ 8 ∙ share

read it
Game Plan: What AI can do for Football, and What Football can do for AI

The rapid progress in artificial intelligence (AI) and machine learning ...
11/18/2020 ∙ by Karl Tuyls, et al. ∙ 11 ∙ share

read it
Behavior Priors for Efficient Reinforcement Learning

As we deploy reinforcement learning agents to solve increasingly challen...
10/27/2020 ∙ by Dhruva Tirumala, et al. ∙ 10 ∙ share

read it
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification

Many real-world physical control systems are required to satisfy constra...
10/20/2020 ∙ by Daniel J. Mankowitz, et al. ∙ 0 ∙ share

read it
Learning Dexterous Manipulation from Suboptimal Experts

Learning dexterous manipulation in high-dimensional state-action spaces ...
10/16/2020 ∙ by Rae Jeong, et al. ∙ 0 ∙ share

read it
Local Search for Policy Iteration in Continuous Control

We present an algorithm for local, regularized, policy improvement in re...
10/12/2020 ∙ by Jost Tobias Springenberg, et al. ∙ 0 ∙ share

read it
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban

Intelligent robots need to achieve abstract objectives using concrete, s...
10/03/2020 ∙ by Peter Karkus, et al. ∙ 18 ∙ share

read it
Learning to swim in potential flow

Fish swim by undulating their bodies. These propulsive motions require c...
09/30/2020 ∙ by Yusheng Jiao, et al. ∙ 0 ∙ share

read it
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Recent work in deep reinforcement learning (RL) has produced algorithms ...
09/11/2020 ∙ by Mehdi Mirza, et al. ∙ 7 ∙ share

read it
Importance Weighted Policy Learning and Adaption

The ability to exploit prior experience to solve novel problems rapidly ...
09/10/2020 ∙ by Alexandre Galashov, et al. ∙ 6 ∙ share

read it
Action and Perception as Divergence Minimization

We introduce a unified objective for action and perception of intelligen...
09/03/2020 ∙ by Danijar Hafner, et al. ∙ 10 ∙ share

read it
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion

Modern Reinforcement Learning (RL) algorithms promise to solve difficult...
08/06/2020 ∙ by Roland Hafner, et al. ∙ 0 ∙ share

read it
Data-efficient Hindsight Off-policy Option Learning

Solutions to most complex tasks can be decomposed into simpler, intermed...
07/30/2020 ∙ by Markus Wulfmeier, et al. ∙ 38 ∙ share

read it
Critic Regularized Regression

Offline reinforcement learning (RL), also known as batch RL, offers the ...
06/26/2020 ∙ by Ziyu Wang, et al. ∙ 32 ∙ share

read it
RL Unplugged: Benchmarks for Offline Reinforcement Learning

Offline methods for reinforcement learning have the potential to help br...
06/24/2020 ∙ by Caglar Gulcehre, et al. ∙ 10 ∙ share

read it
dm_control: Software and Tasks for Continuous Control

The dm_control software package is a collection of Python libraries and ...
06/22/2020 ∙ by Yuval Tassa, et al. ∙ 18 ∙ share

read it
Simple Sensor Intentions for Exploration

Modern reinforcement learning algorithms can learn solutions to increasi...
05/15/2020 ∙ by Tim Hertweck, et al. ∙ 2 ∙ share

read it
A Distributional View on Multi-Objective Policy Optimization

Many real-world problems require trading off multiple competing objectiv...
05/15/2020 ∙ by Abbas Abdolmaleki, et al. ∙ 0 ∙ share

read it
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning

Standard planners for sequential decision making (including Monte Carlo ...
04/23/2020 ∙ by Giambattista Parascandolo, et al. ∙ 27 ∙ share

read it
Value-driven Hindsight Modelling

Value estimation is a critical component of the reinforcement learning (...
02/19/2020 ∙ by Arthur Guez, et al. ∙ 17 ∙ share

read it
Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics

Many real-world control problems involve both discrete decision variable...
01/02/2020 ∙ by Michael Neunert, et al. ∙ 15 ∙ share

read it
Hindsight Credit Assignment

We consider the problem of efficient credit assignment in reinforcement ...
12/05/2019 ∙ by Anna Harutyunyan, et al. ∙ 0 ∙ share

read it
Reusable neural skill embeddings for vision-guided whole body movement and object manipulation

Both in simulation settings and robotics, there is an ambition to produc...
11/15/2019 ∙ by Josh Merel, et al. ∙ 11 ∙ share

read it
Quinoa: a Q-function You Infer Normalized Over Actions

We present an algorithm for learning an approximate action-value soft Q-...
11/05/2019 ∙ by Jonas Degrave, et al. ∙ 20 ∙ share

read it
Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions

A plethora of problems in AI, engineering and the sciences are naturally...
10/15/2019 ∙ by Lars Buesing, et al. ∙ 0 ∙ share

read it
Stabilizing Transformers for Reinforcement Learning

Owing to their ability to both effectively integrate information over lo...
10/13/2019 ∙ by Emilio Parisotto, et al. ∙ 7 ∙ share

read it
Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models

Humans are masters at quickly learning many complex tasks, relying on an...
10/09/2019 ∙ by Arunkumar Byravan, et al. ∙ 5 ∙ share

read it
A Generalized Training Approach for Multiagent Learning

This paper investigates a population-based training regime based on game...
09/27/2019 ∙ by Paul Müller, et al. ∙ 20 ∙ share

read it
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control

Some of the most successful applications of deep reinforcement learning ...
09/26/2019 ∙ by H. Francis Song, et al. ∙ 0 ∙ share

read it
Regularized Hierarchical Policies for Compositional Transfer in Robotics

The successful application of flexible, general learning algorithms -- s...
06/26/2019 ∙ by Markus Wulfmeier, et al. ∙ 1 ∙ share

read it
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces

Direct optimization is an appealing approach to differentiating through ...
06/14/2019 ∙ by Guy Lorberbom, et al. ∙ 3 ∙ share

read it
Meta reinforcement learning as task inference

Humans achieve efficient learning by relying on prior knowledge about th...
05/15/2019 ∙ by Jan Humplik, et al. ∙ 5 ∙ share

read it
Meta-learning of Sequential Strategies

In this report we review memory-based meta-learning as a tool for buildi...
05/08/2019 ∙ by Pedro A. Ortega, et al. ∙ 16 ∙ share

read it
Information asymmetry in KL-regularized RL

Many real world tasks exhibit rich structure that is repeated across dif...
05/03/2019 ∙ by Alexandre Galashov, et al. ∙ 6 ∙ share

read it
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL

As reinforcement learning agents are tasked with solving more challengin...
03/18/2019 ∙ by Dhruva Tirumala, et al. ∙ 20 ∙ share

read it
The Termination Critic

In this work, we consider the problem of autonomously discovering behavi...
02/26/2019 ∙ by Anna Harutyunyan, et al. ∙ 10 ∙ share

read it
Emergent Coordination Through Competition

We study the emergence of cooperative behaviors in reinforcement learnin...
02/19/2019 ∙ by Siqi Liu, et al. ∙ 2 ∙ share

read it
Value constrained model-free continuous control

The naive application of Reinforcement Learning algorithms to continuous...
02/12/2019 ∙ by Steven Bohez, et al. ∙ 0 ∙ share

read it
Credit Assignment Techniques in Stochastic Computation Graphs

Stochastic computation graphs (SCGs) provide a formalism to represent st...
01/07/2019 ∙ by Theophane Weber, et al. ∙ 0 ∙ share

read it
Self-supervised Learning of Image Embedding for Continuous Control

Operating directly from raw high dimensional sensory inputs like images ...
01/03/2019 ∙ by Carlos Florensa, et al. ∙ 0 ∙ share

read it
Relative Entropy Regularized Policy Iteration

We present an off-policy actor-critic algorithm for Reinforcement Learni...
12/05/2018 ∙ by Abbas Abdolmaleki, et al. ∙ 2 ∙ share

read it
Entropic Policy Composition with Generalized Policy Improvement and Divergence Correction

Deep reinforcement learning (RL) algorithms have made great strides in r...
12/05/2018 ∙ by Jonathan J Hunt, et al. ∙ 2 ∙ share

read it
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures

This paper addresses the problem of evaluating learning systems in safet...
12/04/2018 ∙ by Jonathan Uesato, et al. ∙ 6 ∙ share

read it
Neural probabilistic motor primitives for humanoid control

We focus on the problem of learning a single motor module that can flexi...
11/28/2018 ∙ by Josh Merel, et al. ∙ 12 ∙ share

read it
Hierarchical visuomotor control of humanoids

We aim to build complex humanoid agents that integrate perception, motor...
11/23/2018 ∙ by Josh Merel, et al. ∙ 0 ∙ share

read it
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search

Learning policies on data synthesized by models can in principle quench ...
11/15/2018 ∙ by Lars Buesing, et al. ∙ 0 ∙ share

read it
Maximum a Posteriori Policy Optimisation

We introduce a new algorithm for reinforcement learning called Maximum a...
06/14/2018 ∙ by Abbas Abdolmaleki, et al. ∙ 0 ∙ share

read it
Mix&Match - Agent Curricula for Reinforcement Learning

We introduce Mix&Match (M&M) - a training framework designed to facilita...
06/05/2018 ∙ by Wojciech Marian Czarnecki, et al. ∙ 2 ∙ share

read it
Relational inductive biases, deep learning, and graph networks

Artificial intelligence (AI) has undergone a renaissance recently, makin...
06/04/2018 ∙ by Peter W. Battaglia, et al. ∙ 0 ∙ share

read it
Graph networks as learnable physics engines for inference and control

Understanding and interacting with everyday physical scenes requires ric...
06/04/2018 ∙ by Alvaro Sanchez-Gonzalez, et al. ∙ 2 ∙ share

read it

Nicolas Heess

Featured Co-authors