Algorithms

This section highlights the supported NEORL algorithms and how to setup and solve a problem. The algorithms are classified in three separate categories.

• Neural Algorithms (Reinforcement Learning)
  • Advantage Actor Critic (A2C)
  • Actor-Critic with Experience Replay (ACER)
  • Actor Critic using Kronecker-Factored Trust Region (ACKTR)
  • Deep Q Learning (DQN)
  • Proximal Policy Optimisation (PPO)
• Evolutionary and Swarm Algorithms
  • Evolution Strategies (\(\mu,\lambda\)) (ES)
  • Particle Swarm Optimisation (PSO)
  • Heterogeneous comprehensive learning particle swarm optimization (HCLPSO)
  • Differential Evolution (DE)
  • Exponential Natural Evolution Strategies (XNES)
  • Grey Wolf Optimizer (GWO)
  • Simulated Annealing (SA)
  • Salp Swarm Algorithm (SSA)
  • Whale Optimization Algorithm (WOA)
  • Moth-flame Optimization (MFO)
  • JAYA Algorithm
  • Bat Algorithm (BAT)
  • Harris Hawks Optimization (HHO)
  • Ant Colony Optimization (ACO)
  • Cuckoo Search (CS)
  • Tabu Search (TS)
• Hybrid and Neuroevolution Algorithms
  • Feedforward Neuroevolution of Augmenting Topologies (FNEAT)
  • Recurrent Neuroevolution of Augmenting Topologies (RNEAT)
  • Prioritized replay Evolutionary and Swarm Algorithm (PESA)
  • Modern PESA (PESA2)
  • RL-informed Evolution Strategies (PPO-ES)
  • RL-informed Differential Evolution (ACKTR-DE)
  • Neural Genetic Algorithms (NGA)
  • Neural Harris Hawks Optimization (NHHO)
  • Animorphic Ensemble Optimization (AEO)
  • Ensemble of Differential Evolution Variants (EDEV)
  • Ensemble Particle Swarm Optimization (EPSO)