Benjamin Eysenbach

papers

705

total citations

papers (17)

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

ICML 2024arXiv

citations

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

ICLR 2024arXiv

citations

Imitating Past Successes can be Very Suboptimal

NEURIPS 2022arXiv

citations

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions

NEURIPS 2022arXiv

citations

Learning Options via Compression

NEURIPS 2022arXiv

citations

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

ICLR 2024arXiv

citations

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

ICLR 2025arXiv

citations

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

ICLR 2025arXiv

citations

Horizon Generalization in Reinforcement Learning

ICLR 2025arXiv

citations

Contrastive Representations for Temporal Reasoning

NEURIPS 2025arXiv

citations

A Rate-Distortion View of Uncertainty Quantification

ICML 2024arXiv

citations

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

ICLR 2025arXiv

citations

Benjamin Eysenbach

papers (17)

Contrastive Learning as Goal-Conditioned Reinforcement Learning

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

OGBench: Benchmarking Offline Goal-Conditioned RL

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

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

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

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

Imitating Past Successes can be Very Suboptimal

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions

Learning Options via Compression

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

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

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

Horizon Generalization in Reinforcement Learning

Contrastive Representations for Temporal Reasoning

A Rate-Distortion View of Uncertainty Quantification

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

papers (17)

Contrastive Learning as Goal-Conditioned Reinforcement Learning

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

OGBench: Benchmarking Offline Goal-Conditioned RL

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

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

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

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

Imitating Past Successes can be Very Suboptimal

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions

Learning Options via Compression

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

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

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

Horizon Generalization in Reinforcement Learning

Contrastive Representations for Temporal Reasoning

A Rate-Distortion View of Uncertainty Quantification

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