Glen Berseth

Computer Science · Physical Sciences

19h-index2.1kcitations106works10.32yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(42), Evacuation and Crowd Dynamics(21), Robotic Locomotion and Control(16), Robot Manipulation and Learning(15), Human Pose and Action Recognition(7)

Publications106 total

A Comedy of Estimators: On KL Regularization in RL Training of LLMs
ArXiv.org·2025Open Access
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
arXiv (Cornell University)·2025Open Access
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
arXiv (Cornell University)·2025Open Access
SegDAC: Improving Visual Reinforcement Learning by Extracting Dynamic Object-Centric Representations from Pretrained Vision Models
ArXiv.org·2025Open Access
Is Exploration or Optimization the Problem for Deep Reinforcement Learning?
arXiv (Cornell University)·2025Open Access
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
arXiv (Cornell University)·2025Open Access
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
arXiv (Cornell University)·2025Open Access
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
arXiv (Cornell University)·2025· 13 citedOpen Access
Solving Bayesian inverse problems with diffusion priors and off-policy RL
arXiv (Cornell University)·2025Open Access
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
arXiv (Cornell University)·2025Open Access
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
arXiv (Cornell University)·2024Open Access
Adaptive Resolution Residual Networks -- Generalizing Across Resolutions Easily and Efficiently
arXiv (Cornell University)·2024Open Access
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
arXiv (Cornell University)·2024Open Access
Reinforcement learning for versatile, dynamic, and robust bipedal locomotion control
The International Journal of Robotics Research·2024· 88 cited
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
arXiv (Cornell University)·2024· 1 citedOpen Access
Enhancing Agent Learning through World Dynamics Modeling
arXiv (Cornell University)·2024Open Access
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
2024· 93 citedOpen Access
Amortizing intractable inference in diffusion models for vision, language, and control
arXiv (Cornell University)·2024Open Access
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
arXiv (Cornell University)·2024Open Access
page 1 of 6Next →

Frequent Co-authors

Mubbasir Kapadia(20), Petros Faloutsos(20), Sergey Levine(17), Brandon Haworth(15), Muhammad Usman(13), Xue Bin Peng(10), Michiel van de Panne(9), Chelsea Finn(7), Zhongyu Li(6), Koushil Sreenath(6), Dinesh Jayaraman(6), Pieter Abbeel(5), Alexander Khazatsky(5), Coline Devin(5), Jensen Gao(4), Mahyar Khayatkhoei(4), Abdul Rehman(3), Abhiram Maddukuri(3), Annie Xie(3), Archit Sharma(3)