Class

MCAgent

MCAgent(env, confignullable, randomSeednullable)

Implementation of First visit Monte Carlo

Constructor

# new MCAgent(env, confignullable, randomSeednullable)

Parameters:

Name	Type	Attributes	Description
`env`	`Environment`		The environment
`config`	`MCAgentSettings`	<nullable>	The configuration
`randomSeed`	`number`	<nullable>	the random seed

View Source core/src/Agents/MCAgent/MCAgent.ts, line 13

Extends

PersistableAgent

Members

Type: Array.<Experience>

# experience

Get a shallow copy of experiences

View Source core/src/Agents/MCAgent/MCAgent.ts, line 48

Type: Tensor

# stateReturnCountTable

Get the state retunn count table

View Source core/src/Agents/MCAgent/MCAgent.ts, line 41

Type: Tensor

# valueTable

Get the value table

View Source core/src/Agents/MCAgent/MCAgent.ts, line 34

Methods

# abstract config() → {object|undefined}

get the configuration of the agent

Overrides:

PersistableAgent#config

View Source core/src/RLInterface/Agent.ts, line 68

Returns:

Type: object | undefined

# decayEpsilon() → {void}

Decay the epsilon value

View Source core/src/Agents/MCAgent/MCAgent.ts, line 270

Returns:

Type: void

# abstract evalStep(state) → {string}

Method to select an action for prediction

Parameters:

Name	Type	Description
`state`	`object`	The current game state

Overrides:

PersistableAgent#evalStep

View Source core/src/RLInterface/Agent.ts, line 76

Returns:

The action to select next

Type: string

# experience() → {Array}

Get a shallow copy of experiences

View Source core/src/Agents/MCAgent/MCAgent.ts, line 254

Returns:

Type: Array

# abstract feed(prevState, takenAction, newState, payoff, contextInfo) → {Promise.<void>}

this method feed the new game state and reward back for the agent to update their algorithm

Parameters:

Name	Type	Description
`prevState`	`object`	The previous game state
`takenAction`	`string`	The action that was taken.
`newState`	`object`	The new game state
`payoff`	`number`	The gained payoff for the agent
`contextInfo`	`object`	Through this object, additional information can be provided.

Overrides:

PersistableAgent#feed

View Source core/src/RLInterface/Agent.ts, line 51

Returns:

Type: Promise.<void>

# abstract init() → {void}

initialize the agent

Overrides:

PersistableAgent#init

View Source core/src/RLInterface/Agent.ts, line 31

Returns:

Type: void

# abstract load(fileManager, optionsnullable) → {Promise.<void>}

load the Model

Parameters:

Name	Type	Attributes	Description
`fileManager`	`FileStrategy`		FileManager Strategy
`options`	`object`	<nullable>	the options zo use for loading

Overrides:

PersistableAgent#load

View Source core/src/RLInterface/PersistableAgent.ts, line 26

Returns:

Type: Promise.<void>

# abstract loadConfig(fileManager, optionsnullable) → {Promise.<void>}

load the config

Parameters:

Name	Type	Attributes	Description
`fileManager`	`FileStrategy`		FileManager Strategy
`options`	`object`	<nullable>	the options zo use for loading

Overrides:

PersistableAgent#loadConfig

View Source core/src/RLInterface/PersistableAgent.ts, line 35

Returns:

Type: Promise.<void>

# abstract log() → {void}

Interface method for loggin while training

Overrides:

PersistableAgent#log

View Source core/src/RLInterface/Agent.ts, line 83

Returns:

Type: void

# abstract reset() → {void}

Reset the agent

Overrides:

PersistableAgent#reset

View Source core/src/RLInterface/Agent.ts, line 90

Returns:

Type: void

# abstract save(fileManager, optionsnullable) → {Promise.<void>}

Save the model

Parameters:

Name	Type	Attributes	Description
`fileManager`	`FileStrategy`		FileManager Strategy
`options`	`object`	<nullable>	the options to use for saving the agent

Overrides:

PersistableAgent#save

View Source core/src/RLInterface/PersistableAgent.ts, line 44

Returns:

Type: Promise.<void>

# abstract saveConfig(fileManager, optionsnullable) → {Promise.<void>}

Save the Config

Parameters:

Name	Type	Attributes	Description
`fileManager`	`FileStrategy`		FileManager Strategy
`options`	`object`	<nullable>	the options to use for saving the agent

Overrides:

PersistableAgent#saveConfig

View Source core/src/RLInterface/PersistableAgent.ts, line 53

Returns:

Type: Promise.<void>

# setConfig(confignullable, randomSeednullable) → {void}

Set The configuration of the agent after initailizing.

Parameters:

Name	Type	Attributes	Description
`config`	`MCAgentSettings`	<nullable>	The configuration
`randomSeed`	`randomSeed`	<nullable>	The random seed

Overrides:

PersistableAgent#setConfig

View Source core/src/Agents/MCAgent/MCAgent.ts, line 263

Returns:

Type: void

# setRandomSeed(randomSeednullable)

Set the random Seed for the agent

Parameters:

Name	Type	Attributes	Description
`randomSeed`	`number`	<nullable>	the random seed

View Source core/src/Agents/MCAgent/MCAgent.ts, line 128

# stateReturnCountTable() → {Tensor}

Get the state retunn count table

View Source core/src/Agents/MCAgent/MCAgent.ts, line 246

Returns:

Type: Tensor

# abstract step(state) → {string}

Method for selecting a new action for training

Parameters:

Name	Type	Description
`state`	`object`	The current game state

Overrides:

PersistableAgent#step

View Source core/src/RLInterface/Agent.ts, line 39

Returns:

The action to select next

Type: string

# abstract trainingInitialized() → {boolean}

Get whether the agent was correctly initialized for training.

Overrides:

PersistableAgent#trainingInitialized

View Source core/src/RLInterface/Agent.ts, line 24

Returns:

Type: boolean

# valueTable() → {Tensor}

Get the value table

View Source core/src/Agents/MCAgent/MCAgent.ts, line 238

Returns:

Type: Tensor