Add v242 pages

Gemfile

@@ -0,0 +1,15 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+gem 'jekyll'
+
+group :jekyll_plugins do
+  gem 'github-pages'
+  gem 'jekyll-remote-theme'
+  gem 'jekyll-include-cache'
+  gem 'webrick'
+end
+
+# gem "rails"
+

README.md

@@ -0,0 +1,23 @@
+# PMLR 242
+
+To suggest fixes to this volume please make a pull request containing the changes requested and a justification for the changes.
+
+To edit the details of this conference work edit the [_config.yml](./_config.yml) file and submit a pull request.
+
+To make changes to the individual paper details, edit the associated paper file in the [./_posts](./_posts) subdirectory.
+
+For details of how to publish in PMLR please check https://proceedings.mlr.press/faq.html
+
+For details of what is required to submit a proceedings please check https://proceedings.mlr.press/spec.html
+
+
+
+Published as Volume 242 by the Proceedings of Machine Learning Research on 11 June 2024.
+
+Volume Edited by:
+  * Alessandro Abate
+  * Kostas Margellos
+  * Antonis Papachristodoulou
+
+Series Editors:
+  * Neil D. Lawrence

_config.yml

@@ -0,0 +1,83 @@
+---
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+title: Proceedings of Machine Learning Research
+shortname: L4DC
+year: '2024'
+volume: '242'
+start: 2024-07-15
+end: 2024-07-17
+published: 2024-06-11
+layout: proceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: l4dc2024
+month: 0
+tex_title: Proceedings of the 6th Annual Learning for Dynamics & Control Conference
+cycles: false
+bibtex_editor: Abate, Alessandro and Margellos, Kostas and Papachristodoulou, Antonis
+editor:
+- given: Alessandro
+  family: Abate
+- given: Kostas
+  family: Margellos
+- given: Antonis
+  family: Papachristodoulou
+description: |
+  Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+    Held in University of Oxford, Oxford, UK on 15-17 July 2024
+
+  Published as Volume 242 by the Proceedings of Machine Learning Research on 11 June 2024.
+
+  Volume Edited by:
+    Alessandro Abate
+    Kostas Margellos
+    Antonis Papachristodoulou
+
+  Series Editors:
+    Neil D. Lawrence
+date_str: 15--17 Jul
+url: https://proceedings.mlr.press
+author:
+  name: PMLR
+baseurl: "/v242"
+twitter_username: MLResearchPress
+github_username: mlresearch
+markdown: kramdown
+exclude:
+- README.md
+- Gemfile
+- ".gitignore"
+plugins:
+- jekyll-feed
+- jekyll-seo-tag
+- jekyll-remote-theme
+remote_theme: mlresearch/jekyll-theme
+style: pmlr
+permalink: "/:title.html"
+ghub:
+  edit: true
+  repository: v242
+display:
+  copy_button:
+    bibtex: true
+    endnote: true
+    apa: true
+  comments: false
+volume_type: Volume
+volume_dir: v242
+email: ''
+conference:
+  name: 6th Annual Learning for Dynamics \& Control Conference
+  url: https://l4dc.web.ox.ac.uk/
+  location: University of Oxford, Oxford, UK
+  dates:
+  - 2024-07-15
+  - 2024-07-16
+  - 2024-07-17
+analytics:
+  google:
+    tracking_id: UA-92432422-1
+orig_bibfile: "/Users/neil/mlresearch/v242/l4dc2024.bib"
+# Site settings
+# Original source:  /Users/neil/mlresearch/v242/l4dc2024.bib

_posts/2024-06-11-agorio24a.md

@@ -0,0 +1,51 @@
+---
+title: Multi-agent assignment via state augmented reinforcement learning
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+abstract: We address the conflicting requirements of a multi-agent assignment problem
+  through constrained reinforcement learning, emphasizing the inadequacy of standard
+  regularization techniques for this purpose. Instead, we recur to a state augmentation
+  approach in which the oscillation of dual variables is exploited by agents to alternate
+  between tasks. In addition, we coordinate the actions of the multiple agents acting
+  on their local states through these multipliers, which are gossiped through a communication
+  network, eliminating the need to access other agent states. By these means, we propose
+  a distributed multi-agent assignment protocol with theoretical feasibility guarantees
+  that we corroborate in a monitoring numerical experiment.
+layout: inproceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: agorio24a
+month: 0
+tex_title: "{Multi-agent assignment via state augmented reinforcement learning}"
+firstpage: 1
+lastpage: 12
+page: 1-12
+order: 1
+cycles: false
+bibtex_author: Agorio, Leopoldo and Alen, Sean Van and Calvo-Fullana, Miguel and Paternain,
+  Santiago and Bazerque, Juan Andr\'{e}s
+author:
+- given: Leopoldo
+  family: Agorio
+- given: Sean Van
+  family: Alen
+- given: Miguel
+  family: Calvo-Fullana
+- given: Santiago
+  family: Paternain
+- given: Juan Andrés
+  family: Bazerque
+date: 2024-06-11
+address:
+container-title: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+volume: '242'
+genre: inproceedings
+issued:
+  date-parts:
+  - 2024
+  - 6
+  - 11
+pdf: https://proceedings.mlr.press/v242/agorio24a/agorio24a.pdf
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2024-06-11-aguiar24a.md

@@ -0,0 +1,47 @@
+---
+title: Learning flow functions of spiking systems
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+abstract: We propose a framework for surrogate modelling of spiking systems. These
+  systems are often described by stiff differential equations with high-amplitude
+  oscillations and multi-timescale dynamics, making surrogate models an attractive
+  tool for system design.We parameterise the flow function of a spiking system in
+  state-space using a recurrent neural network architecture, allowing for a direct
+  continuous-time representation of the state trajectories which is particularly advantageous
+  for this class of systems.The spiking nature of the signals makes for a data-heavy
+  and computationally hard training process, and we describe two methods to mitigate
+  these difficulties. We demonstrate our framework on two conductance-based models
+  of biological neurons.
+layout: inproceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: aguiar24a
+month: 0
+tex_title: "{Learning flow functions of spiking systems}"
+firstpage: 1
+lastpage: 12
+page: 1-12
+order: 1
+cycles: false
+bibtex_author: Aguiar, Miguel and Das, Amritam and Johansson, Karl H.
+author:
+- given: Miguel
+  family: Aguiar
+- given: Amritam
+  family: Das
+- given: Karl H.
+  family: Johansson
+date: 2024-06-11
+address:
+container-title: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+volume: '242'
+genre: inproceedings
+issued:
+  date-parts:
+  - 2024
+  - 6
+  - 11
+pdf: https://proceedings.mlr.press/v242/aguiar24a/aguiar24a.pdf
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2024-06-11-akgul24a.md

@@ -0,0 +1,51 @@
+---
+title: Continual Learning of Multi-modal Dynamics with External Memory
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+abstract: We study the problem of fitting a model to a dynamical environment when
+  new modes of behavior emerge sequentially. The learning model is aware when a new
+  mode appears, but it cannot access the true modes of individual training sequences.
+  The state-of-the-art continual learning approaches cannot handle this setup, because
+  parameter transfer suffers from catastrophic interference and episodic memory design
+  requires the knowledge of the ground-truth modes of sequences. We devise a novel
+  continual learning method that overcomes both limitations by maintaining a descriptor
+  of the mode of an encountered sequence in a neural episodic memory. We employ a
+  Dirichlet Process prior on the attention weights of the memory to foster efficient
+  storage of the mode descriptors. Our method performs continual learning by transferring
+  knowledge across tasks by retrieving the descriptors of similar modes of past tasks
+  to the mode of a current sequence and feeding this descriptor into its transition
+  kernel as control input. We observe the continual learning performance of our method
+  to compare favorably to the mainstream parameter transfer approach.
+layout: inproceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: akgul24a
+month: 0
+tex_title: "{Continual Learning of Multi-modal Dynamics with External Memory}"
+firstpage: 1
+lastpage: 12
+page: 1-12
+order: 1
+cycles: false
+bibtex_author: Akg\"{u}l, Abdullah and Unal, Gozde and Kandemir, Melih
+author:
+- given: Abdullah
+  family: Akgül
+- given: Gozde
+  family: Unal
+- given: Melih
+  family: Kandemir
+date: 2024-06-11
+address:
+container-title: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+volume: '242'
+genre: inproceedings
+issued:
+  date-parts:
+  - 2024
+  - 6
+  - 11
+pdf: https://proceedings.mlr.press/v242/akgul24a/akgul24a.pdf
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2024-06-11-alboni24a.md

@@ -0,0 +1,60 @@
+---
+title: 'CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory
+  Optimization'
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+abstract: Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful
+  and complementary tools to solve optimal control problems. On the one hand, TO can
+  efficiently compute locally-optimal solutions, but it tends to get stuck in local
+  minima if the problem is not convex. On the other hand, RL is typically less sensitive
+  to non-convexity, but it requires a much higher computational effort. Recently,
+  we have proposed CACTO (Continuous Actor-Critic with Trajectory Optimization), an
+  algorithm that uses TO to guide the exploration of an actor-critic RL algorithm.
+  In turns, the policy encoded by the actor is used to warm-start TO, closing the
+  loop between TO and RL. In this work, we present an extension of CACTO exploiting
+  the idea of Sobolev learning. To make the training of the critic network faster
+  and more data efficient, we enrich it with the gradient of the Value function, computed
+  via a backward pass of the differential dynamic programming algorithm. Our results
+  show that the new algorithm is more efficient than the original CACTO, reducing
+  the number of TO episodes by a factor ranging from 3 to 10, and consequently the
+  computation time. Moreover, we show that CACTO-SL helps TO to find better minima
+  and to produce more consistent results.
+layout: inproceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: alboni24a
+month: 0
+tex_title: "{CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with
+  Trajectory Optimization}"
+firstpage: 1
+lastpage: 12
+page: 1-12
+order: 1
+cycles: false
+bibtex_author: Alboni, Elisa and Grandesso, Gianluigi and Rosati Papini, Gastone Pietro
+  and Carpentier, Justin and Del Prete, Andrea
+author:
+- given: Elisa
+  family: Alboni
+- given: Gianluigi
+  family: Grandesso
+- given: Gastone Pietro
+  family: Rosati Papini
+- given: Justin
+  family: Carpentier
+- given: Andrea
+  family: Del Prete
+date: 2024-06-11
+address:
+container-title: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+volume: '242'
+genre: inproceedings
+issued:
+  date-parts:
+  - 2024
+  - 6
+  - 11
+pdf: https://proceedings.mlr.press/v242/alboni24a/alboni24a.pdf
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2024-06-11-allen-blanchette24a.md

@@ -0,0 +1,47 @@
+---
+title: Hamiltonian GAN
+booktitle: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+abstract: A growing body of work leverages the Hamiltonian formalism as an inductive
+  bias for physically plausible neural network based video generation. The structure
+  of the Hamiltonian ensures conservation of a learned quantity (e.g., energy) and
+  imposes a phase-space interpretation on the low-dimensional manifold underlying
+  the input video. While this interpretation has the potential to facilitate the integration
+  of learned representations in downstream tasks, existing methods are limited in
+  their applicability as they require a structural prior for the configuration space
+  at design time. In this work, we present a GAN-based video generation pipeline with
+  a learned configuration space map and Hamiltonian neural network motion model, to
+  learn a representation of the configuration space from data. We train our model
+  with a physics-inspired cyclic-coordinate loss function which encourages a minimal
+  representation of the configuration space and improves interpretability. We demonstrate
+  the efficacy and advantages of our approach on the Hamiltonian Dynamics Suite Toy
+  Physics dataset.
+layout: inproceedings
+series: Proceedings of Machine Learning Research
+publisher: PMLR
+issn: 2640-3498
+id: allen-blanchette24a
+month: 0
+tex_title: "{Hamiltonian GAN}"
+firstpage: 1
+lastpage: 13
+page: 1-13
+order: 1
+cycles: false
+bibtex_author: Allen-Blanchette, Christine
+author:
+- given: Christine
+  family: Allen-Blanchette
+date: 2024-06-11
+address:
+container-title: Proceedings of the 6th Annual Learning for Dynamics \& Control Conference
+volume: '242'
+genre: inproceedings
+issued:
+  date-parts:
+  - 2024
+  - 6
+  - 11
+pdf: https://proceedings.mlr.press/v242/allen-blanchette24a/allen-blanchette24a.pdf
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---