Romain Laroche

101 papers A* 23A 11B 3Misc 2Journal 40Unranked 22

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Learning Fused State Representations for Control from Multi-View Observations. ICML Zeyu Wang, Yao-Hui Li, Xin Li, Hongyu Zang, Romain Laroche, Riashat Islam
2025	J	`jnl`	Learning Fused State Representations for Control from Multi-View Observations. CoRR Zeyu Wang, Yao-Hui Li, Xin Li, Hongyu Zang, Romain Laroche, Riashat Islam
2025	A*	`conf`	Rejecting Hallucinated State Targets during Planning. ICML Harry Zhao, Tristan Sylvain, Romain Laroche, Doina Precup, Yoshua Bengio
2024	A*	`conf`	Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning. ICLR Harry Zhao, Safa Alver, Harm van Seijen, Romain Laroche, Doina Precup, Yoshua Bengio
2024	A*	`conf`	Think Before You Act: Decision Transformers with Working Memory. ICML Jikun Kang, Romain Laroche, Xingdi Yuan, Adam Trischler, Xue Liu, Jie Fu
2023	A*	`conf`	Behavior Prior Representation learning for Offline Reinforcement Learning. ICLR Hongyu Zang, Xin Li, Jie Yu, Chen Liu, Riashat Islam, Remi Tachet des Combes, Romain Laroche
2023	A*	`conf`	Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. NeurIPS Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets. CoRR Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal
2023	J	`jnl`	Combining Spatial and Temporal Abstraction in Planning for Better Generalization. CoRR Mingde Zhao, Safa Alver, Harm van Seijen, Romain Laroche, Doina Precup, Yoshua Bengio
2023	A*	`conf`	Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting. ICLR Zhang-Wei Hong, Pulkit Agrawal, Remi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting. CoRR Zhang-Wei Hong, Pulkit Agrawal, Rémi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Massive multi-player multi-armed bandits for IoT networks: An application on LoRa networks. Ad Hoc Networks Hiba Dakdouk, Raphaël Féraud, Nadège Varsier, Patrick Maillé, Romain Laroche
2023	A*	`conf`	On the Convergence of SARSA with Linear Function Approximation. ICML Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
2023	A*	`conf`	On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs. ICML Romain Laroche, Remi Tachet des Combes
2023	A	`conf`	One-Shot Learning from a Demonstration with Hierarchical Latent Language. AAMAS Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté, Matthew J. Hausknecht, Romain Laroche, Ida Momennejad, Harm van Seijen, Benjamin Van Durme
2023	J	`jnl`	Think Before You Act: Decision Transformers with Internal Working Memory. CoRR Jikun Kang, Romain Laroche, Xindi Yuan, Adam Trischler, Xue Liu, Jie Fu
2023	A*	`conf`	Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning. NeurIPS Hongyu Zang, Xin Li, Leiji Zhang, Yang Liu, Baigui Sun, Riashat Islam, Remi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning. CoRR Hongyu Zang, Xin Li, Leiji Zhang, Yang Liu, Baigui Sun, Riashat Islam, Remi Tachet des Combes, Romain Laroche
2023	J	`jnl`	Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods. Trans. Mach. Learn. Res. Yuchen Lu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron C. Courville, Alessandro Sordoni
2022	A	`conf`	A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms. AAMAS Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes
2022	J	`jnl`	Behavior Prior Representation learning for Offline Reinforcement Learning. CoRR Hongyu Zang, Xin Li, Jie Yu, Chen Liu, Riashat Islam, Remi Tachet des Combes, Romain Laroche
2022	A	`conf`	Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms. AISTATS Romain Laroche, Remi Tachet des Combes
2022	J	`jnl`	Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms. CoRR Romain Laroche, Remi Tachet des Combes
2022	A*	`conf`	Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning. NeurIPS Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet des Combes
2022	J	`jnl`	Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning. CoRR Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet des Combes
2022	J	`jnl`	Emergence of Shared Sensory-motor Graphical Language from Visual Input. CoRR Yoann Lemesle, Tristan Karch, Romain Laroche, Clément Moulin-Frier, Pierre-Yves Oudeyer
2022	J	`jnl`	Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning. CoRR Yuchen Lu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron C. Courville, Alessandro Sordoni
2022	J	`jnl`	Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch. J. Mach. Learn. Res. Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
2022	J	`jnl`	Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning. CoRR David Brandfonbrener, Remi Tachet des Combes, Romain Laroche
2022	J	`jnl`	Non-Markovian policies occupancy measures. CoRR Romain Laroche, Remi Tachet des Combes, Jacob Buckman
2022	J	`jnl`	On the Chattering of SARSA with Linear Function Approximation. CoRR Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
2022	J	`jnl`	One-Shot Learning from a Demonstration with Hierarchical Latent Language. CoRR Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté, Matthew J. Hausknecht, Romain Laroche, Ida Momennejad, Harm van Seijen, Benjamin Van Durme
2022	A*	`conf`	When does return-conditioned supervised learning work for offline reinforcement learning? NeurIPS David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
2022	J	`jnl`	When does return-conditioned supervised learning work for offline reinforcement learning? CoRR David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
2021	J	`jnl`	Batched Bandits with Crowd Externalities. CoRR Romain Laroche, Othmane Safsafi, Raphaël Féraud, Nicolas Broutin
2021	A*	`conf`	Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates. NeurIPS Romain Laroche, Remi Tachet des Combes
2021	J	`jnl`	Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates. CoRR Romain Laroche, Remi Tachet des Combes
2021	J	`jnl`	Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch. CoRR Shangtong Zhang, Remi Tachet des Combes, Romain Laroche
2021	A*	`conf`	Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs. NeurIPS Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche
2021	J	`jnl`	Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs. CoRR Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche
2021	B	`conf`	The Emergence of the Shape Bias Results from Communicative Efficiency. CoNLL Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche
2021	J	`jnl`	The Emergence of the Shape Bias Results from Communicative Efficiency. CoRR Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche
2020	J	`jnl`	A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms. CoRR Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes
2020	A*	`conf`	Learning Dynamic Belief Graphs to Generalize on Text-Based Games. NeurIPS Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton
2020	J	`jnl`	Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games. CoRR Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton
2020	A*	`conf`	Reinforcement Learning Framework for Deep Brain Stimulation Study. IJCAI Dmitrii Krylov, Remi Tachet des Combes, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov
2020	J	`jnl`	Reinforcement Learning Framework for Deep Brain Stimulation Study. CoRR Dmitrii Krylov, Rémi Tachet des Combes, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov
2020	A	`conf`	Safe Policy Improvement with an Estimated Baseline Policy. AAMAS Thiago D. Simão, Romain Laroche, Rémi Tachet des Combes
2019	A*	`conf`	Budgeted Reinforcement Learning in Continuous State Space. NeurIPS Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
2019	J	`jnl`	Building Dynamic Knowledge Graphs from Text-based Games. CoRR Mikulas Zelinka, Xingdi Yuan, Marc-Alexandre Côté, Romain Laroche, Adam Trischler
2019	A*	`conf`	Decentralized Exploration in Multi-Armed Bandits. ICML Raphaël Féraud, Réda Alami, Romain Laroche
2019	A*	`conf`	Safe Policy Improvement with Baseline Bootstrapping. ICML Romain Laroche, Paul Trichelair, Remi Tachet des Combes
2019	—	`conf`	Safe Policy Improvement with Soft Baseline Bootstrapping. ECML/PKDD (3) Kimia Nadjahi, Romain Laroche, Rémi Tachet des Combes
2019	J	`jnl`	Safe Policy Improvement with Soft Baseline Bootstrapping. CoRR Kimia Nadjahi, Romain Laroche, Rémi Tachet des Combes
2019	J	`jnl`	Safe Policy Improvement with an Estimated Baseline Policy. CoRR Thiago D. Simão, Romain Laroche, Rémi Tachet des Combes
2019	J	`jnl`	Scaling up budgeted reinforcement learning. CoRR Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
2018	J	`jnl`	A methodology for turn-taking capabilities enhancement in Spoken Dialogue Systems using Reinforcement Learning. Comput. Speech Lang. Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2018	J	`jnl`	Counting to Explore and Generalize in Text-based Games. CoRR Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew J. Hausknecht, Adam Trischler
2018	J	`jnl`	Decentralized Exploration in Multi-Armed Bandits. CoRR Raphaël Féraud, Réda Alami, Romain Laroche
2018	—	`conf`	In reinforcement learning, all objective functions are not equal. ICLR (Workshop) Romain Laroche, Harm van Seijen
2018	A*	`conf`	On Value Function Representation of Long Horizon Problems. AAAI Lucas Lehnert, Romain Laroche, Harm van Seijen
2018	—	`conf`	Reinforcement Learning Algorithm Selection. ICLR (Poster) Romain Laroche, Raphaël Féraud
2018	A	`conf`	Training Dialogue Systems With Human Advice. AAMAS Merwan Barlier, Romain Laroche, Olivier Pietquin
2017	J	`jnl`	Algorithm selection of off-policy reinforcement learning algorithm. CoRR Romain Laroche, Raphaël Féraud
2017	—	`conf`	Hybrid Reward Architecture for Reinforcement Learning. NIPS Harm van Seijen, Mehdi Fatemi, Romain Laroche, Joshua Romoff, Tavian Barnes, Jeffrey Tsang
2017	J	`jnl`	Hybrid Reward Architecture for Reinforcement Learning. CoRR Harm van Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche, Tavian Barnes, Jeffrey Tsang
2017	J	`jnl`	Multi-Advisor Reinforcement Learning. CoRR Romain Laroche, Mehdi Fatemi, Joshua Romoff, Harm van Seijen
2017	J	`jnl`	Safe Policy Improvement with Baseline Bootstrapping. CoRR Romain Laroche, Paul Trichelair
2017	J	`jnl`	The Complex Negotiation Dialogue Game. CoRR Romain Laroche
2017	A*	`conf`	Transfer Reinforcement Learning with Shared Dynamics. AAAI Romain Laroche, Merwan Barlier
2016	A	`conf`	A Stochastic Model for Computer-Aided Human-Human Dialogue. INTERSPEECH Merwan Barlier, Romain Laroche, Olivier Pietquin
2016	—	`conf`	Compact and Interpretable Dialogue State Representation with Genetic Sparse Distributed Memory. IWSDS Layla El Asri, Romain Laroche, Olivier Pietquin
2016	J	`jnl`	Improving Scalability of Reinforcement Learning by Separation of Concerns. CoRR Harm van Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche
2016	—	`conf`	Incremental Human-Machine Dialogue Simulation. IWSDS Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2016	—	`conf`	Learning dialogue dynamics with the method of moments. SLT Merwan Barlier, Romain Laroche, Olivier Pietquin
2016	A*	`conf`	Reinforcement Learning for Turn-Taking Management in Incremental Spoken Dialogue Systems. IJCAI Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2016	A	`conf`	Score-based Inverse Reinforcement Learning. AAMAS Layla El Asri, Bilal Piot, Matthieu Geist, Romain Laroche, Olivier Pietquin
2016	—	`conf`	The Negotiation Dialogue Game. IWSDS Romain Laroche, Aude Genevay
2016	—	`conf`	Towards a virtual personal assistant based on a user-defined portfolio of multi-domain vocal applications. SLT Tatiana Ekeinhor-Komi, Jean Léon Bouraoui, Romain Laroche, Fabrice Lefèvre
2016	A	`conf`	Transfer Learning for User Adaptation in Spoken Dialogue Systems. AAMAS Aude Genevay, Romain Laroche
2015	Misc	`conf`	Content finder AssistanT. ICIN Romain Laroche
2015	—	`conf`	Dialogue Efficiency Evaluation of Turn-Taking Phenomena in a Multi-layer Incremental Simulated Environment. HCI (27) Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2015	—	`conf`	Human-Machine Dialogue as a Stochastic Game. SIGDIAL Conference Merwan Barlier, Julien Pérolat, Romain Laroche, Olivier Pietquin
2015	—	`conf`	Optimising Turn-Taking Strategies With Reinforcement Learning. SIGDIAL Conference Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2015	A*	`conf`	Turn-taking phenomena in incremental dialogue systems. EMNLP Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2014	—	`conf`	A simple approach to make dialogue systems incremental (Vers une approche simplifiée pour introduire le caractère incrémental dans les systèmes de dialogue) [in French]. TALN (1) Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2014	—	`conf`	An easy method to make dialogue systems incremental. SIGDIAL Conference Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2014	—	`conf`	CFAsT: Content-Finder AssistanT [in French]. TALN (3) Romain Laroche
2014	—	`conf`	Contextual Bandit for Active Learning: Active Thompson Sampling. ICONIP (1) Djallel Bouneffouf, Romain Laroche, Tanguy Urvoy, Raphaël Féraud, Robin Allesiardo
2014	B	`conf`	DINASTI: Dialogues with a Negotiating Appointment Setting Interface. LREC Layla El Asri, Romain Laroche, Olivier Pietquin
2014	—	`conf`	DictaNum: a dialogue system for numbers dictation (DictaNum : système de dialogue incrémental pour la dictée de numéros.) [in French]. TALN (3) Hatim Khouzaimi, Romain Laroche, Fabrice Lefèvre
2014	—	`conf`	Enia : A customizable multi-domain assistant (Un assistant vocal personnalisable) [in French]. TALN (3) Tatiana Ekeinhor-Komi, Hajar Falih, Christine Chardenon, Romain Laroche, Fabrice Lefèvre
2014	B	`conf`	NASTIA: Negotiating Appointment Setting Interface. LREC Layla El Asri, Rémi Lemonnier, Romain Laroche, Olivier Pietquin, Hatim Khouzaimi
2014	Misc	`conf`	Ordinal regression for interaction quality prediction. ICASSP Layla El Asri, Hatim Khouzaimi, Romain Laroche, Olivier Pietquin
2013	—	`conf`	Reward Shaping for Statistical Optimisation of Dialogue Management. SLSP Layla El Asri, Romain Laroche, Olivier Pietquin
2013	—	`conf`	Will my Spoken Dialogue System be a Slow Learner ? SIGDIAL Conference Layla El Asri, Romain Laroche
2012	—	`conf`	Reward Function Learning for Dialogue Management. STAIRS Layla El Asri, Romain Laroche, Olivier Pietquin
2010	—	`conf`	Enhanced Monitoring Tools and Online Dialogue Optimisation Merged into a New Spoken Dialogue System Design Experience. SIGDIAL Conference Ghislain Putois, Romain Laroche, Philippe Bretier
2010	A	`conf`	Enhanced monitoring tools and online dialogue optimisation merged into a new spoken dialogue system design experience. INTERSPEECH Romain Laroche, Philippe Bretier, Ghislain Putois
2010	A	`conf`	Optimising a handcrafted dialogue system design. INTERSPEECH Romain Laroche, Ghislain Putois, Philippe Bretier
2009	A	`conf`	Hybridisation of expertise and reinforcement learning in dialogue systems. INTERSPEECH Romain Laroche, Ghislain Putois, Philippe Bretier, Bernadette Bouchon-Meunier