Mimicking Evolution With Reinforcement Learning

Abstract

Evolution gave rise to human and animal intelligence here on Earth. We argue that the path to developing artificial human-like-intelligence will pass through mimicking the evolutionary process in a nature-like simulation. In Nature, there are two processes driving the development of the brain: evolution and learning. Evolution acts slowly, across generations, and amongst other things, it defines what agents learn by changing their internal reward function. Learning acts fast, across one's lifetime, and it quickly updates agents' policy to maximise pleasure and minimise pain. The reward function is slowly aligned with the fitness function by evolution, however, as agents evolve the environment and its fitness function also change, increasing the misalignment between reward and fitness. It is extremely computationally expensive to replicate these two processes in simulation. This work proposes Evolution via Evolutionary Reward (EvER) that allows learning to single-handedly drive the sear

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyabrantes2020mimicking

Related papers

• The Evolution Theory Of Learning: From Natural Selection To Reinforcement Learning (2023)0.00
• Evolutionary Reinforcement Learning: A Survey (2023)13.93
• Evolution Of Societies Via Reinforcement Learning (2024)0.00
• Recruitment-imitation Mechanism For Evolutionary Reinforcement Learning (2019)0.00
• Illuminating The Three Dogmas Of Reinforcement Learning Under Evolutionary Light (2025)0.00
• Neuroevolution Of Recurrent Architectures On Control Tasks (2023)4.52
• Differentiable Evolutionary Reinforcement Learning (2025)0.00
• Inclusive Fitness As A Key Step Towards More Advanced Social Behaviors In Multi-agent Reinforcement Learning Settings (2025)0.00