← Authors

Romain Laroche

28 papers · 2015–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (10) 🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (26) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (7) 🌍 Conference Polyglot (9) 🀝 Dynamic Duo (11) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ’Ž Century Club (28) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter ❓ The Questioner ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (93) πŸ”₯ Unstoppable (11)

Conferences

NIPS (9) ICML (7) ICLR (4) EMNLP (2) IJCAI (2) AISTATS (1) CONLL (1) INTERSPEECH (1) JMLR (1)

Top co-authors

Remi Tachet des Combes (11) Hongyu Zang (4) Riashat Islam (4) Xin Li (4) Yoshua Bengio (3) Eva Portelance (2) Xingdi Yuan (2) Raphaël Féraud (2) Michael C. Frank (2) Fabrice Lefèvre (2)

Keywords

offline reinforcement learning (4) value function (3) reinforcement learning (3) policy gradient (2) language acquisition (2) convergence rate (2) shape bia (2) safe policy improvement (2) communicative efficiency (2) neural emergent language (2) safety constraint (2) convergence analysis (1) robotic manipulation (1) markov decision process (1) global convergence (1) self-supervised learning (1) policy optimization (1) sequential decision making (1) risk management (1) finite sample analysis (1)

Papers

Learning Fused State Representations for Control from Multi-View Observations ICML 2025
Rejecting Hallucinated State Targets during Planning ICML 2025
Think Before You Act: Decision Transformers with Working Memory ICML 2024
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning ICLR 2024
On the Convergence of SARSA with Linear Function Approximation ICML 2023
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting ICLR 2023
Behavior Prior Representation learning for Offline Reinforcement Learning ICLR 2023
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets NIPS 2023
Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning NIPS 2023
On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs ICML 2023
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch JMLR 2022
When does return-conditioned supervised learning work for offline reinforcement learning? NIPS 2022
Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning NIPS 2022
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms AISTATS 2022
Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates NIPS 2021
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs NIPS 2021
The Emergence of the Shape Bias Results from Communicative Efficiency EMNLP 2021
The Emergence of the Shape Bias Results from Communicative Efficiency CONLL 2021
Learning Dynamic Belief Graphs to Generalize on Text-Based Games NIPS 2020
Reinforcement Learning Framework for Deep Brain Stimulation Study IJCAI 2020
Safe Policy Improvement with Baseline Bootstrapping ICML 2019
Decentralized Exploration in Multi-Armed Bandits ICML 2019
Budgeted Reinforcement Learning in Continuous State Space NIPS 2019
Reinforcement Learning Algorithm Selection ICLR 2018
Hybrid Reward Architecture for Reinforcement Learning NIPS 2017
Reinforcement Learning for Turn-Taking Management in Incremental Spoken Dialogue Systems IJCAI 2016
A Stochastic Model for Computer-Aided Human-Human Dialogue INTERSPEECH 2016
Turn-taking phenomena in incremental dialogue systems EMNLP 2015