← Authors

Benjamin Eysenbach

41 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (14) πŸƒ Academic Marathon (7) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🏠 Conference Loyalist (23) 🀝 Dynamic Duo (27) πŸ‘‘ Triple Crown πŸ’Ž Century Club (41) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (5) ⚑ Prolific Year (7) ❓ The Questioner (3) πŸ—ƒοΈ Keyword Collector (82)

Conferences

ICLR (23) NIPS (9) ICML (6) CORL (2) L4DC (1)

Top co-authors

Sergey Levine (27) Ruslan Salakhutdinov (13) Vivek Myers (5) Chelsea Finn (5) Chongyi Zheng (4) Tianwei Ni (3) Abhishek Gupta (3) Amrith Setlur (2) Julian Ibarz (2) Pierre-Luc Bacon (2)

Keywords

contrastive learning (5) offline reinforcement learning (5) reinforcement learning (4) representation learning (4) policy optimization (2) model-based planning (2) latent variable model (2) goal-conditioned reinforcement learning (2) latent representation (2) hierarchical reinforcement learning (2) model-based reinforcement learning (2) value function (2) automated planning (1) probabilistic inference (1) information bottleneck (1) label smoothing (1) imitation learning (1) human-robot interaction (1) inverse reinforcement learning (1) multi-task learning (1)

Papers

Horizon Generalization in Reinforcement Learning ICLR 2025
Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research ICLR 2025
OGBench: Benchmarking Offline Goal-Conditioned RL ICLR 2025
The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities ICLR 2025
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning ICLR 2025
A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals ICLR 2025
Learning to Assist Humans without Inferring Rewards NIPS 2024
Bridging State and History Representations: Understanding Self-Predictive RL ICLR 2024
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations ICLR 2024
Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View. ICLR 2024
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data ICLR 2024
Contrastive Difference Predictive Coding ICLR 2024
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making ICML 2024
A Rate-Distortion View of Uncertainty Quantification ICML 2024
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference NIPS 2024
Contrastive Value Learning: Implicit Models for Simple Offline RL CORL 2023
HIQL: Offline Goal-Conditioned RL with Latent States as Actions NIPS 2023
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment NIPS 2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts ICLR 2023
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective ICLR 2023
A Connection between One-Step RL and Critic Regularization in Reinforcement Learning ICML 2023
Contrastive Example-Based Control L4DC 2023
Learning Options via Compression NIPS 2022
Maximum Entropy RL (Provably) Solves Some Robust RL Problems ICLR 2022
Imitating Past Successes can be Very Suboptimal NIPS 2022
Contrastive Learning as Goal-Conditioned Reinforcement Learning NIPS 2022
Mismatched No More: Joint Model-Policy Optimization for Model-Based RL NIPS 2022
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs ICML 2022
RvS: What is Essential for Offline RL via Supervised Learning? ICLR 2022
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks ICLR 2022
The Information Geometry of Unsupervised Reinforcement Learning ICLR 2022
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions NIPS 2022
Rapid Exploration for Open-World Navigation with Latent Goal Models CORL 2021
Model-Based Visual Planning with Self-Supervised Functional Distances ICLR 2021
Learning to Reach Goals via Iterated Supervised Learning ICLR 2021
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers ICLR 2021
C-Learning: Learning to Achieve Goals via Recursive Classification ICLR 2021
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills ICML 2021
Diversity is All You Need: Learning Skills without a Reward Function ICLR 2019
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning ICLR 2018
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings ICML 2018