Tom Silver

@tomssilver

Assistant Professor @Princeton. Developing robots that plan and learn to help people.

Princeton, NJ

tomsilver.github.io

Replies Reposts Media

Tom Silver
@tomssilver
Sep 6
This week's #PaperILike is "Safe Model-based Reinforcement Learning with Stability Guarantees" (Berkenkamp et al., NeurIPS 2017). Some safe RL guarantees the learned policy is safe; this guarantees safety *during* learning. Important for RL in real! PDF:
arxiv.org
Safe Model-based Reinforcement Learning with Stability Guarantees
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible...
1
Tom Silver
@tomssilver
Aug 31
We're excited to announce the 4th Workshop on Learning Effective Abstractions for Planning (LEAP) at #CoRL2026! Previous LEAP papers have gone on to win awards at main conferences (SymSkill, Universal Visual Decomposer). Yes, we'll take all the credit! Workshop link 👇
1
Tom Silver
@tomssilver
Aug 30
This week's #PaperILike is "Deliberate Practice: Learning Robot Skills under a Budget" (Vats et al., 2026). Practice your robot skills in a provably optimal way. Big fan of this whole line; see also arxiv.org/abs/2209.13605 & arxiv.org/abs/2505.00490 PDF: arxiv.org/abs/2608.13415
arxiv.org
Efficient Recovery Learning using Model Predictive Meta-Reasoning
Operating under real world conditions is challenging due to the possibility of a wide range of failures induced by execution errors and state uncertainty. In relatively benign settings, such...
Tom Silver
@tomssilver
Aug 23
This week's #PaperILike is "Sleep-time Compute: Beyond Inference Scaling at Test-time" (Lin et al., 2025). I often wonder what robots should do while they're asleep. One answer: use context to think ahead about likely requests before they arrive. PDF:
arxiv.org
Sleep-time Compute: Beyond Inference Scaling at Test-time
Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce...
4
Tom Silver
@tomssilver
Aug 16
This week's #PaperILike is "Legibility and Predictability of Robot Motion" (Dragan, Lee, & Srinivasa, HRI 2013). Seminal work. Legibility: the robot's goal can be inferred easily from its motion. Predictability is the reverse: goal generates motion. PDF: publications.ri.cmu.edu/legibility-and…