Tuning Proximal Policy Optimization Algorithm in Maze Solving with ML-Agents.
Phan Thanh HungMac Duy Dan TruongPhan Duy HungPublished in: ICACDS (2) (2022)
Keyphrases
- optimization algorithm
- multi objective
- sequential decision making
- multi agent systems
- multi agent
- optimization method
- maximum likelihood
- particle swarm optimization pso
- evolutionary multi objective
- differential evolution
- action selection
- multiple agents
- software agents
- multiagent systems
- optimization strategy
- agent receives
- optimal policy
- pareto optimal
- distributed constraint satisfaction problems
- hybrid optimization algorithm
- reinforcement learning
- autonomous agents
- nsga ii
- artificial bee colony
- markov decision problems
- evolutionary algorithm
- global optima
- multi objective optimization
- control parameters
- combinatorial optimization
- particle swarm optimization
- distributed constraint optimization problems
- objective function
- neuro fuzzy
- fuzzy rules
- resource allocation