Benjamin Eysenbach

CoRR, May, 2025

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities.

[BibT_eX]

[DOI]

CoRR, March, 2025

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

OGBench: Benchmarking Offline Goal-Conditioned RL.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Horizon Generalization in Reinforcement Learning.

[BibT_eX]

[DOI]

Vivek Myers

Catherine Ji

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals.

[BibT_eX]

[DOI]

Grace Liu

Michael Tang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

The "Law" of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities.

[BibT_eX]

[DOI]

Yongwei Che

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

GHIL-Glue: Hierarchical Control with Filtered Subgoal Images.

[BibT_eX]

[DOI]

CoRR, 2024

Accelerating Goal-Conditioned RL Algorithms and Research.

[BibT_eX]

[DOI]

CoRR, 2024

Learning to Assist Humans without Inferring Rewards.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Rate-Distortion View of Uncertainty Quantification.

[BibT_eX]

[DOI]

Ifigeneia Apostolopoulou

Frank Nielsen

Artur Dubrawski

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Contrastive Difference Predictive Coding.

[BibT_eX]

[DOI]

Chongyi Zheng

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Bridging State and History Representations: Understanding Self-Predictive RL.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations.

[BibT_eX]

[DOI]

Stephen Marcus McAleer

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Probabilistic Reinforcement Learning: Using Data to Define Desired Outcomes and Inferring How to Get There

[BibT_eX]

[DOI]

PhD thesis, 2023

A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Stabilizing Contrastive RL: Techniques for Offline Goal Reaching.

[BibT_eX]

[DOI]

CoRR, 2023

HIQL: Offline Goal-Conditioned RL with Latent States as Actions.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Contrastive Example-Based Control.

[BibT_eX]

[DOI]

Proceedings of the Learning for Dynamics and Control Conference, 2023

A Connection between One-Step RL and Critic Regularization in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Contrastive Value Learning: Implicit Models for Simple Offline RL.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2023

2022

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learning Options via Compression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Contrastive Learning as Goal-Conditioned Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Imitating Past Successes can be Very Suboptimal.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs.

[BibT_eX]

[DOI]

Tianwei Ni

Proceedings of the International Conference on Machine Learning, 2022

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

The Information Geometry of Unsupervised Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Maximum Entropy RL (Provably) Solves Some Robust RL Problems.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

RvS: What is Essential for Offline RL via Supervised Learning?

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Recurrent Model-Free RL is a Strong Baseline for Many POMDPs.

[BibT_eX]

[DOI]

Tianwei Ni

CoRR, 2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills.

[BibT_eX]

[DOI]

CoRR, 2021

RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models.

[BibT_eX]

[DOI]

CoRR, 2021

Robust Predictable Control.

[BibT_eX]

[DOI]

Ben Eysenbach

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification.

[BibT_eX]

[DOI]

Ben Eysenbach

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

ViNG: Learning Open-World Navigation with Visual Goals.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Model-Based Visual Planning with Self-Supervised Functional Distances.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Learning to Reach Goals via Iterated Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

C-Learning: Learning to Achieve Goals via Recursive Classification.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Rapid Exploration for Open-World Navigation with Latent Goal Models.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

2020

Learning to be Safe: Deep RL with a Safety Critic.

[BibT_eX]

[DOI]

CoRR, 2020

Interactive Visualization for Debugging RL.

[BibT_eX]

[DOI]

Shuby Deshpande

Jeff Schneider

CoRR, 2020

Weakly-Supervised Reinforcement Learning for Controllable Behavior.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

f-IRL: Inverse Reinforcement Learning via State Marginal Matching.

[BibT_eX]

[DOI]

Proceedings of the 4th Conference on Robot Learning, 2020

2019

Learning To Reach Goals Without Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2019

If MaxEnt RL is the Answer, What is the Question?

[BibT_eX]

[DOI]

CoRR, 2019

Efficient Exploration via State Marginal Matching.

[BibT_eX]

[DOI]

CoRR, 2019

Unsupervised Curricula for Visual Meta-Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning.

[BibT_eX]

[DOI]

Ben Eysenbach

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Diversity is All You Need: Learning Skills without a Reward Function.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Clustervision: Visual Supervision of Unsupervised Clustering.

[BibT_eX]

[DOI]

Christopher deFilippi

Walter F. Stewart

Adam Perer

IEEE Trans. Vis. Comput. Graph., 2018

Unsupervised Meta-Learning for Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2018

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

2016

Who is Mistaken?

[BibT_eX]

[DOI]