Repository for the PGA-MAP-Elites algorithm. PGA-MAP-Elites was developed to efficiently scale MAP-Elites to large genotypes and noisy domains. It uses Neuroevolution driven by a Genetic Algorithm (GA) coupled with Policy Gradients (PG) derived from an off-policy Deep Reinforcement Learning method.
Contributions:30 commits, 23 pushes, 1 branch in 1 year
deep-reinforcement-learninggenetic-algorithmneuroevolution
Repository for the QDgym code. A framework for Quality Diversity optimization benchmark tasks based OpenAI Gym.
Contributions:15 commits, 8 pushes in 7 months
openai-gym