Timezone: »
Learning meaningful behaviors in the absence of a task-specific reward function is a challenging problem in reinforcement learning. A desirable unsupervised objective is to learn a set of diverse skills that provide a thorough coverage of the state space while being directed, i.e., reliably reaching distinct regions of the environment. At test time, an agent could then leverage these skills to solve sparse reward problems by performing efficient exploration and finding an effective goal-directed policy with little-to-no additional learning. Unfortunately, it is challenging to learn skills with such properties, as diffusing (e.g., stochastic policies performing good coverage) skills are not reliable in targeting specific states, whereas directed (e.g., goal-based policies) skills provide limited coverage. In this paper, inspired by the mutual information framework, we propose a novel algorithm designed to maximize coverage while ensuring a constraint on the directedness of each skill. In particular, we design skills with a decoupled policy structure, with a first part trained to be directed and a second diffusing part that ensures local coverage. Furthermore, we leverage the directedness constraint to adaptively add or remove skills as well as incrementally compose them along a tree that is grown to achieve a thorough coverage of the environment. We illustrate how our learned skills enable to efficiently solve sparse-reward downstream tasks in navigation environments, comparing favorably with existing baselines.
Author Information
Pierre-Alexandre Kamienny (Facebook)
Jean Tarbouriech (Facebook AI Research & Inria)
Alessandro Lazaric (Facebook AI Research)
Ludovic Denoyer (Criteo)
More from the Same Authors
-
2020 : Probing Dynamic Environments with Informed Policy Regularization »
Pierre-Alexandre Kamienny -
2021 : Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection »
Matteo Papini · Andrea Tirinzoni · Aldo Pacchiano · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 : A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs »
Andrea Tirinzoni · Matteo Pirotta · Alessandro Lazaric -
2021 : Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret »
Jean Tarbouriech · Jean Tarbouriech · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2021 : A general sample complexity analysis of vanilla policy gradient »
Rui Yuan · Robert Gower · Alessandro Lazaric -
2021 : Exploration-Driven Representation Learning in Reinforcement Learning »
Akram Erraqabi · Mingde Zhao · Marlos C. Machado · Yoshua Bengio · Sainbayar Sukhbaatar · Ludovic Denoyer · Alessandro Lazaric -
2023 Poster: Deep Generative Symbolic Regression with Monte-Carlo-Tree-Search »
Pierre-Alexandre Kamienny · Guillaume Lample · sylvain lamprier · Marco Virgolin -
2023 Poster: Controllable Neural Symbolic Regression »
Tommaso Bendinelli · Luca Biggio · Pierre-Alexandre Kamienny -
2023 Poster: Layered State Discovery for Incremental Autonomous Exploration »
Liyu Chen · Andrea Tirinzoni · Alessandro Lazaric · Matteo Pirotta -
2022 Workshop: Responsible Decision Making in Dynamic Environments »
Virginie Do · Thorsten Joachims · Alessandro Lazaric · Joelle Pineau · Matteo Pirotta · Harsh Satija · Nicolas Usunier -
2022 Poster: Deep symbolic regression for recurrence prediction »
Stéphane d'Ascoli · Pierre-Alexandre Kamienny · Guillaume Lample · Francois Charton -
2022 Spotlight: Deep symbolic regression for recurrence prediction »
Stéphane d'Ascoli · Pierre-Alexandre Kamienny · Guillaume Lample · Francois Charton -
2022 Poster: Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2022 Spotlight: Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2021 : Invited Talk by Alessandro Lazaric »
Alessandro Lazaric -
2021 Poster: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Spotlight: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Poster: Reinforcement Learning with Prototypical Representations »
Denis Yarats · Rob Fergus · Alessandro Lazaric · Lerrel Pinto -
2021 Spotlight: Reinforcement Learning with Prototypical Representations »
Denis Yarats · Rob Fergus · Alessandro Lazaric · Lerrel Pinto -
2020 Poster: No-Regret Exploration in Goal-Oriented Reinforcement Learning »
Jean Tarbouriech · Evrard Garcelon · Michal Valko · Matteo Pirotta · Alessandro Lazaric -
2020 Poster: Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation »
Marc Abeille · Alessandro Lazaric -
2020 Poster: Learning Near Optimal Policies with Low Inherent Bellman Error »
Andrea Zanette · Alessandro Lazaric · Mykel Kochenderfer · Emma Brunskill -
2020 Poster: Meta-learning with Stochastic Linear Bandits »
Leonardo Cella · Alessandro Lazaric · Massimiliano Pontil -
2020 Poster: Near-linear time Gaussian process optimization with adaptive batching and resparsification »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2018 Poster: Improved large-scale graph learning through ridge spectral sparsification »
Daniele Calandriello · Alessandro Lazaric · Ioannis Koutis · Michal Valko -
2018 Oral: Improved large-scale graph learning through ridge spectral sparsification »
Daniele Calandriello · Alessandro Lazaric · Ioannis Koutis · Michal Valko -
2018 Poster: Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric · Ronald Ortner -
2018 Poster: Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems »
Marc Abeille · Alessandro Lazaric -
2018 Oral: Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems »
Marc Abeille · Alessandro Lazaric -
2018 Oral: Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric · Ronald Ortner