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 substantial domain knowledge to design. An alternative is to derive objectives directly from the system dynamics. Empowerment, defined as the c...
Wooyoung Chung, Tristan A. Shah, Volodymyr Makarenko et al.· 0 citations
Controllable Information Production (CIP) is introduced, a novel IM method explicitly grounded in dynamical systems and OC that consistently outperforms prior IM methods on standard benchmarks in robot learning and solves tasks they fail on, including humanoid self-righting.
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 new task. Unsupervised RL aims to reduce this engineering with intrinsic motivation (IM): reward signals that emerge from the agent environ...
Tristan A. Shah, Wooyoung Chung, Volodomyr Makarenko et al.· 0 citations
It is observed that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock.
Tristan A. Shah, I. Nemenman, Daniel Polani et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
