AC
Aaron Courville
cs.LGcs.AIstat.MLcs.CLcs.CVcs.NEcs.SDeess.AScs.MAcs.RO
On Valency
published · living versionsW_8ujrvbgj·v1 · currentpublished
Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data
with Sami Nur Islam, Johan Obando-Ceron, Doina Precup, Pablo Samuel Castro
1 version
W_rjz3mxgb·v1published
Preprints & journals
232 papers in the corpus · 2006–2026FeaTok: Feature-Loss Tokenization for Image Generation2610.22060v1 · Zhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez et al.2026 · 0 citationsarXiv
GitSwarm: Decentralized Compounding Inference2610.04862v1 · Vedant Shah, Ankur Samanta, Paras Dahal et al.2026 · 0 citationsarXiv
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up2609.13443v1 · Michael Noukhovitch, Hamish Ivison, Nathan Lambert et al.2026 · 0 citationsarXiv
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation2609.08798v2 · Youngrok Park, Sangmin Bae, Hojung Jung et al.2026 · 0 citationsarXiv
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling2608.16844v1 · Reza Bayat, Ali Behrouz, Vahab Mirrokni et al.2026 · 0 citationsarXiv
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control2608.07870v1 · Donghu Kim, Youngdo Lee, Hojoon Lee et al.2026 · 0 citationsarXiv
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective2607.02292v1 · Juan Agust'in Duque, Sergio Garc'ia Heredia, Vinicius Hernandes et al.2026 · 0 citationsarXiv
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity2606.26091v1 · Andrei Liviu Nicolicioiu, Mohammad Pezeshki, Aaron Courville2026 · 0 citationsarXiv
Data Selection Through Iterative Self-Filtering for Vision-Language Settings2606.23611v1 · Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M. Moss et al.2026 · 0 citationsarXiv
Tapered Language Models2606.23670v1 · Reza Bayat, Ali Behrouz, Aaron Courville2026 · 0 citationsarXiv
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning2606.05555v1 · Johan Obando-Ceron, Lu Li, Scott Fujimoto et al.2026 · 0 citationsarXiv
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions2606.03382v2 · Bingxu Liu, Jiashun Liu, Johan Obando-Ceron et al.2026 · 0 citationsarXiv
Why Open Source? A Game-Theoretic Analysis of the AI Race2604.16227v1 · Andjela Mladenovic, Aaron Courville, Gauthier Gidel2026 · 0 citationsarXiv
A Mechanistic Analysis of Looped Reasoning Language Models2604.11791v1 · Hugh Blayney, 'Alvaro Arroyo, Johan Obando-Ceron et al.2026 · 0 citationsarXiv
Stable Deep Reinforcement Learning via Isotropic Gaussian Representations2602.19373v3 · Ali Saheb Pasand, Johan Obando-Ceron, Aaron Courville et al.2026 · 0 citationsarXiv
Towards Sustainable Investment Policies Informed by Opponent Shaping2602.11829v1 · Juan Agustin Duque, Razvan Ciuca, Ayoub Echchahed et al.2026 · 0 citationsarXiv
A Comedy of Estimators: On KL Regularization in RL Training of LLMs2512.21852v4 · Vedant Shah, Johan Obando-Ceron, Vineet Jain et al.2025 · 0 citationsarXiv
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks2512.22255v2 · Abhranil Chandra, Ayush Agrawal, Arian Hosseini et al.2025 · 0 citationsarXiv
Learning Robust Social Strategies with Large Language Models2511.19405v2 · Dereck Piche, Mohammed Muqeeth, Milad Aghajohari et al.2025 · 0 citationsarXiv
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction2511.17879v4 · Yusong Wu, Stephen Brade, Aleksandra Teng Ma et al.2025 · 0 citationsarXiv
Evolution Strategies at the Hyperscale2511.16652v2 · Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque et al.2025 · 0 citationsarXiv
The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models2510.19557v2 · Zhang Xiaofeng, Aaron Courville, Michal Drozdzal et al.2025 · 0 citationsarXiv
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents2510.13704v2 · Johan Obando-Ceron, Walter Mayor, Samuel Lavoie et al.2025 · 0 citationsarXiv
The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning2510.06557v3 · Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad et al.2025 · 0 citationsarXiv
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning2510.01656v3 · Jiashun Liu, Johan Obando-Ceron, Han Lu et al.2025 · 0 citationsarXiv
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation2508.06781v1 · Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro et al.2025 · 0 citationsarXiv
Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models2507.12318v3 · Samuel Lavoie, Michael Noukhovitch, Aaron Courville2025 · 0 citationsarXiv
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation2507.10524v3 · Sangmin Bae, Yujin Kim, Reza Bayat et al.2025 · 3 citationsarXiv
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning2506.15544v2 · Roger Creus Castanyer, Johan Obando-Ceron, Lu Li et al.2025 · 0 citationsarXiv
Adaptive Accompaniment with ReaLchords2506.14723v1 · Yusong Wu, Tim Cooijmans, Kyle Kastner et al.2025 · 0 citationsarXiv
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning2506.13672v1 · Jiashun Liu, Johan Obando-Ceron, Pablo Samuel Castro et al.2025 · 0 citationsarXiv
Bias Analysis in Unconditional Image Generative Models2506.09106v1 · Xiaofeng Zhang, Michelle Lin, Simon Lacoste-Julien et al.2025 · 0 citationsarXiv
World Modelling Improves Language Model Agents2506.02918v2 · Shangmin Guo, Omar Darwiche Domingues, Raphael Avalos et al.2025 · 0 citationsarXiv
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks2506.03404v1 · Walter Mayor, Johan Obando-Ceron, Aaron Courville et al.2025 · 0 citationsarXiv
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn2506.00592v1 · Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro et al.2025 · 0 citationsarXiv
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning2505.24061v2 · Jiashun Liu, Zihao Wu, Johan Obando-Ceron et al.2025 · 1 citationarXiv
FLAM: Frame-Wise Language-Audio Modeling2505.05335v2 · Yusong Wu, Christos Tsirigotis, Ke Chen et al.2025 · 0 citationsarXiv
Adaptive Computation Pruning for the Forgetting Transformer2504.06949v2 · Zhixuan Lin, Johan Obando-Ceron, Xu Owen He et al.2025 · 0 citationsarXiv
Forgetting Transformer: Softmax Attention with a Forget Gate2503.02130v2 · Zhixuan Lin, Evgenii Nikishin, Xu Owen He et al.2025 · 1 citationarXiv
Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study2410.17980v2 · Shawn Tan, Songlin Yang, Aaron Courville et al.2024 · 0 citationsarXiv
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models2410.18252v3 · Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux et al.2024 · 0 citationsarXiv
Neuroplastic Expansion in Deep Reinforcement Learning2410.07994v3 · Jiashun Liu, Johan Obando-Ceron, Aaron Courville et al.2024 · 1 citationarXiv
VinePPO: Refining Credit Assignment in RL Training of LLMs2410.01679v2 · Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance et al.2024 · 1 citationarXiv
Not All LLM Reasoners Are Created Equal2410.01748v1 · Arian Hosseini, Alessandro Sordoni, Daniel Toyama et al.2024 · 3 citationsarXiv
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL2410.01930v2 · Ghada Sokar, Johan Obando-Ceron, Aaron Courville et al.2024 · 0 citationsarXiv
Managing multiple agents by automatically adjusting incentives2409.02960v1 · Shunichi Akatsuka, Yaemi Teramoto, Aaron Courville2024 · 0 citationsarXiv
SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning2407.03036v1 · Bac Nguyen, Stefan Uhlich, Fabien Cardinaux et al.2024 · 1 citationarXiv
GenRL: Multimodal-foundation world models for generalization in embodied agents2406.18043v2 · Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt et al.2024 · 5 citationsarXiv
On the consistency of hyper-parameter selection in value-based deep reinforcement learning2406.17523v3 · Johan Obando-Ceron, Joao G.M. Ara'ujo, Aaron Courville et al.2024 · 0 citationsarXiv
Advantage Alignment Algorithms2406.14662v3 · Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans et al.2024 · 1 citationarXiv
Career total: 379 works. 232 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.