- Generated by
1.12.0
|
FoPra Beluga Challenge - Reinforcement Learning v1.0
Deep Reinforcement Learning solution for the Beluga Challenge shipping container optimization problem using PPO and MCTS
|
This is the complete list of members for rl.mcts.mcts_node.MCTSNode, including all inherited members.
| __init__(self, state, parent=None, action=None, depth=0) | rl.mcts.mcts_node.MCTSNode | |
| action | rl.mcts.mcts_node.MCTSNode | |
| add_child(self, child) | rl.mcts.mcts_node.MCTSNode | |
| backpropagate(self, reward) | rl.mcts.mcts_node.MCTSNode | |
| best_child(self, exploration_weight=1.0) | rl.mcts.mcts_node.MCTSNode | |
| children | rl.mcts.mcts_node.MCTSNode | |
| children | rl.mcts.mcts_node.MCTSNode | |
| depth | rl.mcts.mcts_node.MCTSNode | |
| expand(self, tuple candidate) | rl.mcts.mcts_node.MCTSNode | |
| get_untried_action(self) | rl.mcts.mcts_node.MCTSNode | |
| is_fully_expanded(self) | rl.mcts.mcts_node.MCTSNode | |
| is_root(self) | rl.mcts.mcts_node.MCTSNode | |
| is_terminal(self) | rl.mcts.mcts_node.MCTSNode | |
| parent | rl.mcts.mcts_node.MCTSNode | |
| state | rl.mcts.mcts_node.MCTSNode | |
| total_reward | rl.mcts.mcts_node.MCTSNode | |
| visits | rl.mcts.mcts_node.MCTSNode |
1.12.0