Extraction and Transfer of Knowledge in Reinforcement Learning

Presentation of “Reinforcement learning and transfer of knowledge” at PDAI organized by AfIA

Two papers on multi-armed bandit accepted at AI&Stats’16

We had two papers accepted at AI&Stats’16 on multi-armed bandit exploiting the arm structure to...

Presentation of “Reinforcement learning and transfer of knowledge” at PDAI organized by AfIA

Alessandro Lazaric is giving an invited talk at the “Journée pour la promotion et le...

ExTra-Learn is a JCJC-ANR project on "Transfer in Reinforcement Learning" at SequeL (Inria Lille - Nord Europe).
Our objective is to develop novel transfer learning algorithms with the ultimate goal of enabling
reinforcement learning algorithms to continuously improve their performance over time.

Description

ExTra-Learn investigates how reinforcement learning can be enhanced by a transfer approach where the learner leverages over the experience collected in solving multiple tasks to improve the learning performance.

ExTra-Learn is funded by ANR through the JCJC program and it is hosted at INRIA Lille within the SequeL team and it is managed by A. Lazaric.

ExTra-Learn is organized over three main tasks investigating different aspects of transfer in reinforcement learning.

Here you can find all the publications and talks related to ExTra-Learn.

Four papers on multi-armed bandit and reinforcement learning accepted at AI&Stats’17

We had four papers accepted at AI&Stats’17 on multi-armed bandit and reinforcement learning. The most interesting result is the first regret bound on learning in MDPs with options. For the …

One paper accepted at CAp’16 on “Parallel Higher Order Alternating Least Square for Tensor Recommender System”

We are going to present one novel parallel algorithm to perform alternating least squares for tensor completion applied to recommendation systems. Parallel Higher Order Alternating Least Square for Tensor Recommender …

Two papers on multi-armed bandit accepted at AI&Stats’16

We had two papers accepted at AI&Stats’16 on multi-armed bandit exploiting the arm structure to reduce the regret in reward maximization and the probability of error in best-arm identification. Online …

Presentation of “Reinforcement learning and transfer of knowledge” at PDAI organized by AfIA

Alessandro Lazaric is giving an invited talk at the “Journée pour la promotion et le developpement de l’intelligence artificielle” organized by AfIA. Reinforcement Learning and Transfer of Knowledge Reinforcement learning …

Two papers on apprenticeship learning at IJCAI’15

We presented two novel results on apprenticeship learning at IJCAI’15, where we use demonstrations generated by an expert to learn near-optimal policies. This scenario is typical in source-to-target transfer, where the …

Presentation of “Challenges of multi-task and transfer in reinforcement learning” at Dagstuhl seminar

Alessandro Lazaric gave an invited talk on “Challenges of multi-task and transfer in reinforcement learning” at the “Machine Learning with Interdependent and Non-identically Distributed Data” seminar in Dagstuhl. [slides] [abstract]

Ph.D. proposal on “Transfer in multi-armed bandit and reinforcement learning”

Keywords: reinforcement learning, multi-armed bandit, transfer learning, exploration-exploitation, representation learning, hierarchical learning. Research Topic This main objective of this Ph.D. research project is to advance the state-of-the-art in the field of multi-armed …

Extraction and Transfer of Knowledge in Reinforcement Learning

Two papers on multi-armed bandit accepted at AI&Stats’16

Presentation of “Reinforcement learning and transfer of knowledge” at PDAI organized by AfIA

Description

Consortium

Structure

Publications

Four papers on multi-armed bandit and reinforcement learning accepted at AI&Stats’17

One paper accepted at CAp’16 on “Parallel Higher Order Alternating Least Square for Tensor Recommender System”

Two papers on multi-armed bandit accepted at AI&Stats’16

Presentation of “Reinforcement learning and transfer of knowledge” at PDAI organized by AfIA

Two papers on apprenticeship learning at IJCAI’15

Presentation of “Challenges of multi-task and transfer in reinforcement learning” at Dagstuhl seminar

Ph.D. proposal on “Transfer in multi-armed bandit and reinforcement learning”

One paper accepted at NIPS’14 on multi-armed bandit on graphs

Presentation of “Multi-task Linear Bandits” @NIPS’14 Workshop on Transfer and Multi-task Learning

Publication of “Sparse Multi-Task Reinforcement Learning” @NIPS’14