Tom Silver

Welcome to my academic website. You are probably here to see pictures of my dog. Otherwise, read on.

I am a third year computer science PhD student at MIT. I am advised by Leslie Kaelbling and Josh Tenenbaum and am a member of the Learning and Intelligent Systems group and the Computational Cognitive Science group. I am grateful for support from an NSF Graduate Research Fellowship and an MIT Presidential Fellowship. Previously I was a researcher at Vicarious AI. I received my B.A. from Harvard in computer science and mathematics in 2016.

Feel free to contact me at tslvr@mit.edu.

[Google Scholar] [Twitter]

My research uses insights from program synthesis, classical planning, reinforcement learning, and machine learning to improve sample efficiency and generalization in decision-making tasks with very long horizons and sparse rewards.

We propose a bottom-up relational approach for learning operators for task and motion planning. Our approach can be seen as a "model-based" learning approach to TAMP. We compare with several model-free baselines.

We propose a graph neural network architecture for predicting object importance to address the challenge of planning in problems that contain many, many objects.

We propose goal-literal babbling (GLIB), a simple and general method that addresses the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards.

We observe that learning to impose constraints in factored planning problems can induce context-specific abstractions that afford much more efficient planning.

We present PDDLGym, a framework that automatically constructs OpenAI Gym environments from PDDL domains and problems.

We define a class of TAMP problems and survey algorithms for solving them, characterizing the solution methods in terms of their strategies for solving the continuous-space subproblems and their techniques for integrating the discrete and continuous components of the search.

We present an architecture capable of inferring an agent's goals online from both optimal and non-optimal sequences of actions.

We present a framework for learning constraint-based task and motion planning models using gradient descent.

We learn lifted, goal-conditioned policies and use STRIPS planning with learned operator descriptions to solve a large suite of unseen test tasks.

We can learn policies from five or fewer demonstrations that generalize to dramatically different test task instances.

We present a representation for describing transition models in complex uncertain domains using relational rules.

We present a model that learns mode constraints from expert demonstrations. We show that it is data efficient, and that it learns interpretable representations that it can leverage to effectively plan in out-of-distribution environments.

We present a model that starts out with a language of low-level physical constraints and, by observing expert demonstrations, builds up a library of high-level concepts that afford planning and action understanding.

We present a simple method for improving nondifferentiable policies using model-free deep reinforcement learning.

We propose an interactive, behavior-based model that represents concepts using sensorimotor contingencies grounded in an agent's experience.

We introduce the Schema Network, an object-oriented generative physics simulator capable of disentangling multiple causes of events and reasoning backward through causes to achieve goals.

I implement a two-player game and a rating system to measure machine intelligence via crowdsourcing.

Template from here.