Properties of task environments.

We can identify fairly small number of dimensions along which task environments can be categorized.

1] Fully observable Vs Partially Observable.

If an agents sensors give it access to the complete state of the environment at each point in time, then we say that the task environment is fully observable. A task environment is effectively fully observable if the sensors detect all aspects that are relevor to the choice of action, relevance depends on the performance measure. Fully observable environments are convenient because the agent need not maintain any internal state to keep track of the world. An environment might be partially observable because of noisy and inaccurate sensors missing from the sensor data.

Example: A vacuum agent with only a local dirt sensor cannot tell whether there is dirt in other squares.

2] Deterministic Vs stochastic.

If the next state of the environment is completely determined by the current state and the action executed by the agent then we say the environment is deterministic otherwise it is stochastic.

3] Episodic Vs Sequential.

In an episodic task environment, the agent experience is divided into atomic episodes each episode consists of the agent perceiving and then performing a single action. Crucially, the next episode does not depend on the actions taken in previous episodes. In episodic environment, the choice of action in each episode depends only on the episode itself. Many classification tasks are episodes.

Example: An agent that has to spot defective parts on an assembly line bases each decision on the current part, regardless of previous decisions moreover, the current decision doesn’t affect whether the next part is defective. In sequential environments, the current decision could affect all future decisions.

Example: Chess and taxi driving are sequential, in both cases, short term actions can have long term consequences.

Episodic environment are much simpler than sequential environments because the agent does not need to think ahead.

4] Static Vs Dynamics.

If the environment can change white an agent is delebrating then we say the environment is dynamic for that agent otherwise, it is static. Static environments are easy to deal with because the agent need not keep looking at the world while it is deciding on an action, nor need it worry about the passage of time. Dynamic environments are continuously asking the agent what it wants to do, if it has not decided yet , that counts as deciding to do nothing. If the environment itself does not change with the passage of time but the agents performance score does, then we say the environment is semi dynamic.

Example: Taxi driving is clearly dynamic, the other cars and the taxi itself keep moving while the driving algorithm dithers about what to do next. Chess when played with a clock is semi dynamic crossword, puzzles are static.

5] Discrete Vs Continuous.

The discrete/continuous distinction can be applied to the state of the environment, to the way time is Handled and to the percepts and actions of the agent.

Example: A discrete state environment such as a chess game has a finite no of distinct states chess also has a discrete set of percepts and actions.

Taxi driving is a continuous state and continuous time problem: the speed and location of the taxi and of the other vehicles sweep through a range of continuous values and o so smoothly over time. Taxi driving actions are also continuous. Input from digital cameras is discrete.

6] Single Agent Vs Multi Agent.

The distinction between single agent and multi agent environment may seen simple enough.

Example: An agent solving a crossword puzzle by itself is clearly in a single agent chess is in a two agents environment. Chess is a competitive multi agent environment. In a taxi driving environment, avoiding collisions maximizes the performance measure. Of all agents, so it is partially cooperative multi agent environment.

Task Environment Observable Determines Episodic Static Discrete Agent
Crossword Puzzle Fully Determines Sequential Static Discrete Single
Chess with clock Fully Strategic Sequential Static Discrete Multi
Poker Partially Strategic Sequential Static Discrete Multi
Backgammon Fully Stochastic - Static Discrete Multi
Taxi driving Partially Stochastic Sequential Dynamic Con Multi
Medical Diagnosis Partially Stochastic Sequential Dynamic Con Single
Image Analysis Fully Deterministic Episodic Semi Con Single
Part pick mg robot Partially Stochastic Episodic Dynamic Con Single
Refing controller Partially Stochastic Sequential Dynamic Con Single
Interstice English tutor Partially Stochastic Sequential Dynamic Discrete Multi

Examples of task environment and their characteristics.

page aisc • 13k  views

Continue reading

Find answer to specific questions by searching them here. It's the best way to discover useful content.

Find more