6 papers
A Unified Framework for Empowerment and Predictive Control
Wooyoung Chung, Tristan Shah, Volodymyr Makarenko +1
Sampling-based model predictive control (MPC) is a powerful approach to trajectory optimization, but its performance depends on an informative cost function that often requires sub…
Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
Tristan Shah, Wooyoung Chung, Volodomyr Makarenko +2
Reinforcement learning (RL) is a powerful paradigm for training agents, yet its success rests on domain expertise of human engineers who design informative reward signals for every…
Multi-Agent Empowerment and Emergence of Complex Behavior in Groups
Tristan Shah, Ilya Nemenman, Daniel Polani +1
Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In…
Emergence of Physical Intelligence via Controllable Information Production
Tristan Shah, Stas Tiomkin
Intrinsic Motivation (IM) aims to train agents without external rewards, enabling useful behavior to emerge from the agent's interaction with its environment alone. However, the do…
Acoustic Wave Manipulation Through Sparse Robotic Actuation
Tristan Shah, Noam Smilovich, Feruza Amirkulova +2
Recent advancements in robotics, control, and machine learning have facilitated progress in the challenging area of object manipulation. These advancements include, among others, t…
Taming Waves: A Physically-Interpretable Machine Learning Framework for Realizable Control of Wave Dynamics
Tristan Shah, Feruza Amirkulova, Stas Tiomkin
Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical const…