default search action
Johan S. Obando-Ceron
- > Home > Persons > Johan S. Obando-Ceron
Publications
- 2026
- [i35]Ali Saheb Pasand, Johan S. Obando-Ceron, Aaron C. Courville, Pouya Bashivan, Pablo Samuel Castro:
Stable Deep Reinforcement Learning via Isotropic Gaussian Representations. CoRR abs/2602.19373 (2026) - [i34]Hugh Blayney, Alvaro Arroyo, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Michael M. Bronstein, Xiaowen Dong:
A Mechanistic Analysis of Looped Reasoning Language Models. CoRR abs/2604.11791 (2026) - [i32]Bingxu Liu, Jiashun Liu, Johan S. Obando-Ceron, Hao Wang, Runze Liu, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions. CoRR abs/2606.03382 (2026) - [i31]Johan S. Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon, Aaron C. Courville, Pablo Samuel Castro:
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning. CoRR abs/2606.05555 (2026) - 2025
- [c17]Jiashun Liu, Johan S. Obando-Ceron, Aaron C. Courville, Ling Pan:
Neuroplastic Expansion in Deep Reinforcement Learning. ICLR 2025 - [c15]Ghada Sokar, Johan S. Obando-Ceron, Aaron C. Courville, Hugo Larochelle, Pablo Samuel Castro:
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL. ICLR 2025 - [c14]Jiashun Liu, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning. ICML 2025 - [c13]Walter Mayor, Johan S. Obando-Ceron, Aaron C. Courville, Pablo Samuel Castro:
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks. ICML 2025 - [c12]Hongyao Tang, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Glen Berseth:
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn. ICML 2025 - [c10]Roger Creus Castanyer, Johan S. Obando-Ceron, Lu Li, Pierre-Luc Bacon, Glen Berseth, Aaron C. Courville, Pablo Samuel Castro:
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning. NeurIPS 2025 - [c8]Jiashun Liu, Zihao Wu, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning. NeurIPS 2025 - [i29]Zhixuan Lin, Johan S. Obando-Ceron, Xu Owen He, Aaron C. Courville:
Adaptive Computation Pruning for the Forgetting Transformer. CoRR abs/2504.06949 (2025) - [i27]Jiashun Liu, Zihao Wu, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning. CoRR abs/2505.24061 (2025) - [i26]Hongyao Tang, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Glen Berseth:
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn. CoRR abs/2506.00592 (2025) - [i25]Walter Mayor, Johan S. Obando-Ceron, Aaron C. Courville, Pablo Samuel Castro:
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks. CoRR abs/2506.03404 (2025) - [i24]Jiashun Liu, Johan S. Obando-Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning. CoRR abs/2506.13672 (2025) - [i23]Roger Creus Castanyer, Johan S. Obando-Ceron, Lu Li, Pierre-Luc Bacon
, Glen Berseth, Aaron C. Courville, Pablo Samuel Castro:
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning. CoRR abs/2506.15544 (2025) - [i21]Jiashun Liu, Johan S. Obando-Ceron, Han Lu, Yancheng He, Weixun Wang, Wenbo Su, Bo Zheng, Pablo Samuel Castro, Aaron C. Courville, Ling Pan:
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning. CoRR abs/2510.01656 (2025) - [i20]Johan S. Obando-Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron C. Courville, Pablo Samuel Castro:
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents. CoRR abs/2510.13704 (2025) - [i16]Vedant Shah, Johan S. Obando-Ceron, Vineet Jain, Brian R. Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron C. Courville:
A Comedy of Estimators: On KL Regularization in RL Training of LLMs. CoRR abs/2512.21852 (2025) - 2024
- [j2]Johan S. Obando-Ceron, João Guilherme Madeira Araújo, Aaron C. Courville, Pablo Samuel Castro:
On the consistency of hyper-parameter selection in value-based deep reinforcement learning. RLJ 3: 1037-1059 (2024) - [c6]Johan S. Obando-Ceron, Aaron C. Courville, Pablo Samuel Castro:
In value-based deep reinforcement learning, a pruned network is a good network. ICML 2024: 38495-38519 - [i14]Johan S. Obando-Ceron, Aaron C. Courville, Pablo Samuel Castro:
In deep reinforcement learning, a pruned network is a good network. CoRR abs/2402.12479 (2024) - [i13]Johan S. Obando-Ceron, João G. M. Araújo, Aaron C. Courville, Pablo Samuel Castro:
On the consistency of hyper-parameter selection in value-based deep reinforcement learning. CoRR abs/2406.17523 (2024) - [i11]Ghada Sokar, Johan S. Obando-Ceron, Aaron C. Courville, Hugo Larochelle, Pablo Samuel Castro:
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL. CoRR abs/2410.01930 (2024) - [i10]Jiashun Liu, Johan S. Obando-Ceron, Aaron C. Courville, Ling Pan:
Neuroplastic Expansion in Deep Reinforcement Learning. CoRR abs/2410.07994 (2024) - 2023
- [c3]Max Schwarzer, Johan S. Obando-Ceron, Aaron C. Courville, Marc G. Bellemare, Rishabh Agarwal, Pablo Samuel Castro:
Bigger, Better, Faster: Human-level Atari with human-level efficiency. ICML 2023: 30365-30380 - [i6]Max Schwarzer, Johan S. Obando-Ceron, Aaron C. Courville, Marc G. Bellemare, Rishabh Agarwal, Pablo Samuel Castro:
Bigger, Better, Faster: Human-level Atari with human-level efficiency. CoRR abs/2305.19452 (2023)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-08-18 00:02 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.