Joshua B. Tenenbaum

Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation

2020 · arXiv (Cornell University)

Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success in many complex tasks, these algorithms need a large number of samples …

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

2021 · arXiv (Cornell University)

Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expertise at the world's oldest board games and many …

Incorporating Rich Social Interactions Into MDPs

2022 · 2022 International Conference on Robotics and Automation (ICRA)

Much of what we do as humans is engage socially with other agents, a skill that robots must also eventually possess. We demonstrate that a rich theory of social interactions originating from microsociology can be …

Neural Amortized Inference for Nested Multi-agent Reasoning

2023 · arXiv (Cornell University)

Multi-agent interactions, such as communication, teaching, and bluffing, often rely on higher-order social inference, i.e., understanding how others infer oneself. Such intricate reasoning can be effectively modeled through nested multi-agent reasoning. Nonetheless, the computational complexity …

Adaptive Social Learning using Theory of Mind

2025

Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don’t always choose to observe others, since social learning can carry time and cognitive resource costs. How do …

A Domain-Specific Probabilistic Programming Language for Reasoning About Reasoning (or: a memo on memo)

2025

The human ability to think about thinking ("theory of mind") is a fundamental object of study in many disciplines. In recent decades, researchers across these disciplines have converged on a rich computational paradigm for modeling …