Tom Silver

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

I am a final year computer science PhD student at MIT. I am advised by Leslie Kaelbling and Joshua 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 tomssilver@gmail.com.

[Google Scholar] [Twitter]


Job Market

I am on the faculty job market. My CV and statements are below:

[CV] [Research Statement] [Teaching Statement] [Diversity Statement]

News

Blog Posts


Research

My research is motivated by the prospect of broadly-competent intelligent robots that can respond to very high-level commands like "make me a heart-healthy dinner"; learn new skills like "grind fresh pepper"; and learn new concepts like "wilted spinach." Such robots would be especially transformative for people who could not otherwise remain independent in their homes. Most of my work is at the intersection of automated planning and machine learning: learning to plan and planning to learn while making efficient use of limited data and time. I often use techniques from task and motion planning, program synthesis, and neuro-symbolic machine learning. Below are selected works; see Google Scholar for a full list.

Learning Abstractions for Robot Planning

Abstractions can be very useful for decision making because they allow the agent to first focus on the high-level aspects of a task before getting bogged down in details. We would like a robot to synthesize abstractions — state abstractions (predicates), action abstractions (skills), and task abstractions (relevant objects) — that are most useful for planning in its specific domain.

Learning State and Action Abstractions

Predicate invention for bilevel planning
Tom Silver*, Rohan Chitnis*, Nishanth Kumar, Willie McClinton, Tomas Lozano-Perez, Leslie Kaelbling, Joshua Tenenbaum
AAAI, 2023. Also appeared at RLDM, 2022 (Spotlight Talk).
[BibTeX] [Code] [PDF]

We learn neuro-symbolic and relational state and action abstractions from demonstrations. The abstractions are explicitly optimized for effective and efficient bilevel planning.

Learning neuro-symbolic skills for bilevel planning
Tom Silver, Ashay Athalye, Joshua Tenenbaum, Tomas Lozano-Perez, Leslie Kaelbling
Conference on Robot Learning (CoRL), 2022
[BibTeX] [Video] [Code] [PDF]

We learn neuro-symbolic skills with goal-conditioned policies from demonstrations and symbolic predicates. The learned skills can be used with bilevel task and motion planning techniques.

Discovering state and action abstractions for generalized task and motion planning
Aidan Curtis, Tom Silver, Joshua Tenenbaum, Tomas Lozano-Perez, Leslie Kaelbling
AAAI, 2022
[BibTeX] [Code] [PDF]

We study generalized planning in robotic settings that involve both discrete and continuous actions. We propose a method for learning state and action abstractions that leads to much faster decision-making over planning from scratch.

Learning symbolic operators for task and motion planning
Tom Silver*, Rohan Chitnis*, Joshua Tenenbaum, Leslie Kaelbling, Tomas Lozano-Perez
IROS, 2021 (Best Paper Award Finalist, Top 5)
[BibTeX] [Video] [Code] [PDF]

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.

Learning Task Abstractions

Planning with learned object importance in large problem instances using graph neural networks
Tom Silver*, Rohan Chitnis*, Aidan Curtis, Joshua Tenenbaum, Tomas Lozano-Perez, Leslie Kaelbling
AAAI, 2021
[BibTeX] [Video] [Code] [PDF]

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

CAMPs: Learning context-specific abstractions for efficient planning in factored MDPs
Rohan Chitnis*, Tom Silver*, Beomjoon Kim, Leslie Kaelbling, Tomas Lozano-Perez
Conference on Robot Learning (CoRL), 2020 (Plenary Talk, Top 20)
[BibTeX] [Video] [Code] [PDF]

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

Learning Policies for Rapid Decision Making

Planning is important when the robot is faced with difficult and unfamiliar problems. But once the robot gets into the habit of solving the same kinds of problems repeatedly, its decision making should become fast and "second nature." In other words, the robot should compile its planning experience into a reactive policy.

Generalized planning in PDDL domains with pretrained large language models
Tom Silver, Soham Dan, Kavitha Srinivas, Joshua Tenenbaum, Leslie Kaelbling, Michael Katz
AAAI, 2024.
[BibTeX] [Code] [PDF]

We use GPT-4 to synthesize Python generalized plans for PDDL domains. We also propose an automated debugging scheme that dramatically improves performance over one-time prompting.

PG3: Policy-guided planning for generalized policy generation
Ryan Yang*, Tom Silver*, Aidan Curtis, Tomas Lozano-Perez, Leslie Kaelbling
IJCAI, 2022. Also appeared at ICAPS PRL Workshop, 2022.
[BibTeX] [Code] [PDF]

We propose a new method for generalized policy search. The main idea is that a candidate policy should be used to guide planning on training problems as a mechanism for evaluating that candidate.

Few-shot Bayesian imitation learning with logical program policies
Tom Silver, Kelsey Allen, Leslie Kaelbling, Joshua Tenenbaum
AAAI 2020. Also appeared at RLDM, 2019 and ICLR SPiRL Workshop.
[BibTeX] [PDF] [Website] [Code] [Video]

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

Residual policy learning
Tom Silver*, Kelsey Allen*, Joshua Tenenbaum, Leslie Kaelbling
arXiv, 2018
[BibTeX] [PDF] [Website] [Code] [Video]

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

Learning to Improve Decision Making through Online Exploration

An intelligent robot should actively collect its own data, and learn from that data, so that it can make better decisions in the future. If an expert is available to provide demonstrations or answer questions, the robot should ask for help, but should do so judiciously.

Embodied active learning of relational state abstractions for bilevel planning
Amber Li, Tom Silver (Oral, Top 12)
Conference on Lifelong Learning Agents (CoLLAs), 2023
[BibTeX] [PDF] [Code]

We consider a setting where a robotic agent must learn the meaning of predicates by querying an expert about the current world state. Before generating an informative query, the robot must take actions to reach an interesting world state.

GLIB: Efficient exploration for relational model-based reinforcement learning via goal-literal babbling
Rohan Chitnis*, Tom Silver*, Joshua Tenenbaum, Leslie Kaelbling, Tomas Lozano-Perez
AAAI, 2021
[BibTeX] [Video] [Code] [PDF]

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.

PDDLGym: Gym environments from PDDL problems
Tom Silver, Rohan Chitnis
ICAPS PRL Workshop, 2020
[BibTeX] [Code] [PDF]

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

Schema networks: zero-shot transfer with a generative causal model of intuitive physics
Ken Kansky, Tom Silver, David A. Mely, Mohamed Eldawy, Miguel Lazaro-Gredilla, Xinghua Lou, Nimrod Dorfman, Szymon Sidor, Scott Phoenix, Dileep George
ICML, 2017
[BibTeX] [PDF] [Blog Post] [Video] [Press Coverage: TechCrunch, Wired, Science]

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.


Template from here.