← Authors

Remi Tachet des Combes

20 papers · 2019–2023 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (5) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (27) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸŒ‰ Interdisciplinary Bridge 🀝 Dynamic Duo (11) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (5) πŸ’Ž Century Club (20) πŸ—ƒοΈ Keyword Collector (84) ⚑ Prolific Year (5)

Conferences

ICML (6) NIPS (6) ICLR (4) AISTATS (1) EACL (1) IJCAI (1) JMLR (1)

Top co-authors

Romain Laroche (11) Hongyu Zang (4) Xin Li (4) Riashat Islam (4) Han Zhao (3) Shangtong Zhang (2) Alessandro Sordoni (2) Philip Bachman (2) Ioannis Mitliagkas (1) Thang Long Doan (1)

Keywords

representation learning (4) value function (2) convergence rate (2) policy gradient (2) domain adaptation (2) reinforcement learning (2) offline reinforcement learning (2) robotic manipulation (1) continual learning (1) policy optimization (1) visual observation (1) variational inference (1) contrastive learning (1) out-of-distribution generalization (1) convergence analysis (1) global convergence (1) adversarial learning (1) mutual information (1) learning theory (1) deep reinforcement learning (1)

Papers

Behavior Prior Representation learning for Offline Reinforcement Learning ICLR 2023
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting ICLR 2023
Learning Structured Representations by Embedding Class Hierarchy ICLR 2023
Principled Offline RL in the Presence of Rich Exogenous Information ICML 2023
On the Convergence of SARSA with Linear Function Approximation ICML 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
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
Adversarial score matching and improved sampling for image generation ICLR 2021
Increasing Robustness to Spurious Correlations using Forgettable Examples EACL 2021
Decomposed Mutual Information Estimation for Contrastive Representation Learning ICML 2021
Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates NIPS 2021
A single gradient step finds adversarial examples on random two-layers neural networks NIPS 2021
Reinforcement Learning Framework for Deep Brain Stimulation Study IJCAI 2020
Deep Reinforcement and InfoMax Learning NIPS 2020
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift NIPS 2020
Safe Policy Improvement with Baseline Bootstrapping ICML 2019
On Learning Invariant Representations for Domain Adaptation ICML 2019