Embodied intelligence via learning and evolution | Nature Communications
The authors propose a new framework, deep evolutionary reinforcement learning, evolves agents with diverse morphologies to learn hard locomotion and manipulation tasks in complex environments, and reveals insights into relations between environmental physics, embodied intelligence, and the evolution of rapid learning.
Download PDF Subjects Computational science Computer science Abstract The intertwined processes of learning and evolution in complex environmental niches have resulted in a remarkable diversity of morphological forms. Moreover, many aspects of animal intelligence are deeply embodied in these evolved morphologies. However, the principles governing relations between environmental complexity, evolved morphology, and the learnability of intelligent control, remain elusive, because performing large-scale in silico experiments on evolution and learning is challenging. Here, we introduce Deep Evoluti
Explore this link on the map →related reading
- Evolution as Backstop for Reinforcement Learning · Gwern.netgwern.net
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- State of Robot Learning, December 2025vedder.io
- pdfopenreview.net
- From motor control to embodied intelligence — Google DeepMinddeepmind.google
- Generalist - GEN-1: Scaling Embodied Foundation Models to Masterygeneralistai.com
- Plasticity as the Mirror of Empowerment (David Abel) - Sensorimotor AI Journal Clubsensorimotorai.github.io
- These weird virtual creatures mutate their bodies to solve problems | MIT Technology Reviewtechnologyreview.com
- Learning dexterity | OpenAIopenai.com
- Illuminating the Three Dogmas of RL under Evolutionary Light (Mani Hamidi) - Sensorimotor AI Journal Clubsensorimotorai.github.io
- Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
- EdgeBench | Scaling Laws of Environment Learningedge-bench.org