Characteristics: The next state of the environment is entirely determined by the current state and the actions taken. There is no randomness involved.
Example: Chess, where the outcome of each move is determined by the rules of the game.
2. Stochastic Environment:
Characteristics: Involves an element of randomness, and the outcome of actions may have probabilistic effects on the state transitions.
Example: Backgammon, where the roll of a die introduces randomness into the game.
3. Static Environment:
Characteristics: Elements and their relationships remain constant over time. Changes occur only when the agent takes actions.
Example: Puzzle-solving scenarios where the environment does not change unless the agent interacts with it.
4. Dynamic Environment:
Characteristics: Elements and their relationships can change autonomously, even without the agent's actions. The environment evolves over time.
Example: Traffic management, where the movement of vehicles changes dynamically over time.
5. Fully Observable Environment:
Characteristics: The AI agent has access to complete and accurate information about the current state of the environment at any given time.
Example: A chess board where the positions of all pieces are visible.
6. Partially Observable Environment:
Characteristics: The AI agent does not have complete information about the current state, requiring inference or estimation based on available observations.
Example: Poker, where the cards held by opponents are hidden.
7. Single-Agent Environment:
Characteristics: The AI system operates in isolation, without interaction with other agents.
Example: A weather prediction system that analyzes data to forecast weather conditions.
8. Multi-Agent Environment:
Characteristics: The AI system interacts with other agents, which may have their objectives and actions, leading to a more complex and dynamic environment.
Example: Competitive games like soccer, where multiple agents (players) interact with each other.
