Natasha Jaques
Assistant Professor, University of Washington | Research Scientist, Google DeepMind | Multi-Agent RL Pioneer
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Natasha Jaques. Every entry undergoes editorial source verification.
PAIRED: Emergent Complexity and Zero-shot Transfer via Adversarial Environment Generation
Invented Protagonist Antagonist Induced Regret Environment Design (PAIRED), using an adversarial teacher agent to procedurally generate training curriculums that optimize agent regret and zero-shot out-of-distribution transfer.
Adversarial curriculum generators can encounter unstable training dynamics when reward estimation variances are high.
Emergent Social Learning via Multi-Agent Reinforcement Learning
Demonstrated that multi-agent reinforcement learning with intrinsic social curiosity incentives enables agents to spontaneously acquire social learning, imitation, and cultural transmission without human expert demonstrations.
Social imitation policies can converge to suboptimal collective traps if demonstrator agents experience local reward plateaus.