Macro-Action
Macro-Action is a large-scale, goal-oriented behavior or task that involves multiple smaller steps to achieve a significant outcome.
Markov Decision Process
Markov Decision Process is a mathematical framework used to model decision-making where outcomes are partly random and partly under the control of a decision-maker.
MCTS Backpropagation
MCTS Backpropagation is the process in Monte Carlo Tree Search where simulation results are propagated up the search tree to update node values and guide future decisions.
MCTS Simulation
MCTS Simulation is a process within Monte Carlo Tree Search where random or guided plays are run to estimate the potential outcomes of moves in decision-making problems.
Mean Field Game
Mean Field Game is a mathematical framework used to analyze decision-making in large populations of interacting agents by approximating their collective behavior.
Minimax
Minimax is a decision-making algorithm used in game theory and artificial intelligence to minimize the possible loss for a worst-case scenario while maximizing potential gains.
Model-Based RL
Model-Based RL is a type of reinforcement learning where an agent builds and uses a predictive model of the environment to plan and make decisions.
Model-Free RL
Model-Free RL is a type of reinforcement learning where the agent learns optimal behaviors without building a model of the environment's dynamics.
Modified Policy Iteration
Modified Policy Iteration is a reinforcement learning algorithm that blends elements of policy evaluation and policy improvement to efficiently find optimal policies.
Monte Carlo Methods
Monte Carlo Methods are computational algorithms that use random sampling to solve complex mathematical problems and simulate systems with uncertain variables.
Monte Carlo Tree Search
Monte Carlo Tree Search is a heuristic search algorithm used for making decisions in complex environments by combining tree search and random sampling.
Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning is a branch of machine learning where multiple agents learn and interact within a shared environment to achieve individual or collective goals through trial and error.