FoPra Beluga Challenge - Reinforcement Learning v1.0
Deep Reinforcement Learning solution for the Beluga Challenge shipping container optimization problem using PPO and MCTS
Classes | Variables
rl.mcts.mcts_node Namespace Reference

Classes

class  MCTSNode
 Node class for Monte Carlo Tree Search. More...
 

Variables

list complex_actions = ["left_stack_rack", "right_stack_rack", "left_unstack_rack", "right_unstack_rack"]
 

Variable Documentation

◆ complex_actions

list rl.mcts.mcts_node.complex_actions = ["left_stack_rack", "right_stack_rack", "left_unstack_rack", "right_unstack_rack"]