A type of machine learning where agents learn by interacting with environments to maximize cumulative rewards.

A model-free reinforcement learning algorithm that learns the value of actions in states to inform decision-making.

An extension of Q-learning that uses deep neural networks to approximate Q-values for complex environments.

Autonomous entities that perceive their environment and take actions to achieve specific goals.

A mathematical framework for modeling strategic interactions among rational decision-makers.

A function that estimates the expected return or value of being in a given state.

The dilemma of choosing between exploring new actions or exploiting known rewarding actions.

Feedback received from the environment that indicates the success of an action taken by the agent.

A parameter that determines the present value of future rewards, balancing short-term and long-term gains.

A strategy or mapping from states to actions that defines the agent's behavior.

An on-policy reinforcement learning algorithm that updates the action-value function based on the current policy.

A subset of machine learning that uses neural networks with many layers to model complex patterns.

A fundamental recursive equation used to compute the value function in reinforcement learning.

A technique where past experiences are stored and reused to improve learning efficiency.

A separate neural network used in DQNs to stabilize learning by providing consistent target values.

An approach that builds a model of the environment to predict outcomes and improve learning.

Parameters set before training that govern the learning process, such as learning rate and discount factor.

Applying knowledge gained in one task to improve learning in a related task.

Using a function to estimate value functions or policies when dealing with large state spaces.

Systems where multiple agents interact, often requiring coordination and competition.

A virtual space where agents can interact, learn, and be evaluated without real-world consequences.

The process of assessing an agent's effectiveness based on predefined metrics and benchmarks.

The process of identifying and resolving errors or issues in code during implementation.

The practice of improving the performance and efficiency of algorithms or models.

A simulation modeling technique that focuses on individual agents and their interactions.