Search papers, labs, and topics across Lattice.
Affiliation:
6
0
5
A frozen graph backbone effectively preserves past structural knowledge in continual multi-agent reinforcement learning, dramatically reducing forgetting and boosting transfer across tasks with distinct graph structures.
Humanoid flips can now be made dramatically safer by selecting policies based on predicted viability, slashing head impacts by over 80% in simulation.
Robots can achieve impressive manipulation skills using only proprioception, revealing the untapped potential of joint encoder signals in dexterous tasks.
Robots can now adapt to drastic physical changes in real-time, maintaining stable locomotion even with a locked leg or added weight.
