ASTEROID distillation teaches in-context exploration under partial observability
Across 11 environments it reports about 2x returns, about 100x fewer interactions than RL, and +40% real-robot success.
4 stories, newest first · one card per story
Across 11 environments it reports about 2x returns, about 100x fewer interactions than RL, and +40% real-robot success.
PIP improves zero-shot multi-agent coordination when partners are intermittently out of view.
HIDE benchmarks robotic memory under partial observability, and SEEK's combined memory raises task success.

KTH researchers trained a reinforcement-learning intrusion response agent on an emulated segmented OT network that autonomously resets hosts and processes to disrupt intruders.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views