Benjamin Eysenbach

Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Intention-Conditioned Flow Occupancy Models

Demystifying The Mechanisms Behind Emergent Exploration in Goal-Conditioned RL

Is Temporal Difference Learning the Gold Standard for Stitching in RL?

Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances

SLAP: Shortcut Learning for Abstract Planning

Value Flows

Consistent Zero-Shot Imitation with Contrastive Goal Inference

UpSkill: Mutual Information Skill learning for Structured Response Diversity in LLMs

Training LLM Agents to Empower Humans

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

BuilderBench -- A benchmark for generalist agents

Horizon Reduction Makes RL Scalable

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

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

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

OGBench: Benchmarking Offline Goal-Conditioned RL

Normalizing Flows are Capable Models for Continuous Control

Contrastive Representations for Temporal Reasoning

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

Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations

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

Horizon Generalization in Reinforcement Learning