Peter Vrancx

is this you? claim profile

0 followers
Vrije Universiteit Brussel

Compatible features for Monotonic Policy Improvement

Recent policy optimization approaches have achieved substantial empirica...
10/09/2019 ∙ by Marcin B. Tomczak, et al. ∙ 0 ∙ share

read it
Policy Optimization Through Approximated Importance Sampling

Recent policy optimization approaches (Schulman et al., 2015a, 2017) hav...
10/09/2019 ∙ by Marcin B. Tomczak, et al. ∙ 0 ∙ share

read it
Disentangled Skill Embeddings for Reinforcement Learning

We propose a novel framework for multi-task reinforcement learning (MTRL...
06/21/2019 ∙ by Janith C. Petangoda, et al. ∙ 1 ∙ share

read it
Model-Based Stabilisation of Deep Reinforcement Learning

Though successful in high-dimensional domains, deep reinforcement learni...
09/06/2018 ∙ by Felix Leibfried, et al. ∙ 0 ∙ share

read it
Learning High-level Representations from Demonstrations

Hierarchical learning (HL) is key to solving complex sequential decision...
02/19/2018 ∙ by Garrett Andersen, et al. ∙ 0 ∙ share

read it
Learning with Options that Terminate Off-Policy

A temporally abstract action, or an option, is specified by a policy and...
11/10/2017 ∙ by Anna Harutyunyan, et al. ∙ 0 ∙ share

read it
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets

Many real-world reinforcement learning problems have a hierarchical natu...
08/22/2017 ∙ by Denis Steckelmacher, et al. ∙ 0 ∙ share

read it
Forecasting day-ahead electricity prices in Europe: the importance of considering market integration

Motivated by the increasing integration among electricity markets, in th...
08/01/2017 ∙ by Jesus Lago, et al. ∙ 0 ∙ share

read it
Analysing Congestion Problems in Multi-agent Reinforcement Learning

Congestion problems are omnipresent in today's complex networks and repr...
02/28/2017 ∙ by Roxana Rădulescu, et al. ∙ 0 ∙ share

read it
An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments

This paper explores the performance of fitted neural Q iteration for rei...
12/17/2015 ∙ by Denis Steckelmacher, et al. ∙ 0 ∙ share

read it
Off-Policy Reward Shaping with Ensembles

Potential-based reward shaping (PBRS) is an effective and popular techni...
02/11/2015 ∙ by Anna Harutyunyan, et al. ∙ 0 ∙ share

read it
Off-Policy Shaping Ensembles in Reinforcement Learning

Recent advances of gradient temporal-difference methods allow to learn o...
05/21/2014 ∙ by Anna Harutyunyan, et al. ∙ 0 ∙ share

read it

Peter Vrancx

Featured Co-authors

Doina Precup

Ann Nowé

Diederik M. Roijers

Pierre-Luc Bacon

Haitham Bou-Ammar

Anna Harutyunyan

Felix Leibfried

Jordi Grau-Moya

Enrique Munoz de Cote

Vincent Adam

Denis Steckelmacher

Compatible features for Monotonic Policy Improvement

Policy Optimization Through Approximated Importance Sampling

Disentangled Skill Embeddings for Reinforcement Learning

Model-Based Stabilisation of Deep Reinforcement Learning

Learning High-level Representations from Demonstrations

Learning with Options that Terminate Off-Policy

Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets

Forecasting day-ahead electricity prices in Europe: the importance of considering market integration

Analysing Congestion Problems in Multi-agent Reinforcement Learning

An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments

Off-Policy Reward Shaping with Ensembles

Off-Policy Shaping Ensembles in Reinforcement Learning