FoPra Beluga Challenge - Reinforcement Learning v1.0
Deep Reinforcement Learning solution for the Beluga Challenge shipping container optimization problem using PPO and MCTS
Classes
rl.agents.high_level.ppo_agent Namespace Reference

Classes

class  ActorNetwork
 Actor network for PPO agent. More...
 
class  CriticNetwork
 Critic network for PPO agent. More...
 
class  PPOAgent
 Proximal Policy Optimization (PPO) agent implementation. More...
 
class  PPOMemory
 Memory buffer for storing PPO training experiences. More...