armaze

type Actions int32 //enums:enum

type Arm struct {

	// length of arm: distance from CS start to US end for this arm
	Length int

	// range of different effort levels per step (uniformly randomly sampled per step) for going down this arm
	Effort minmax.F32

	// index of US present at the end of this arm -- -1 if none
	US int

	// index of CS visible at the start of this arm, -1 if none
	CS int

	// current expected value = US.Prob * US.Mag * Drives-- computed at start of new approach
	ExValue float32 `edit:"-"`

	// current expected PVpos value = normalized ExValue -- computed at start of new approach
	ExPVpos float32 `edit:"-"`

	// current expected PVneg value = normalized time and effort costs
	ExPVneg float32 `edit:"-"`

	// current expected utility = effort discounted version of ExPVpos -- computed at start of new approach
	ExUtil float32 `edit:"-"`
}

type Config struct {

	// experimental paradigm that governs the configuration and updating of environment state over time and the appropriate evaluation criteria.
	Paradigm Paradigms

	// for debugging, print out key steps including a trace of the action generation logic
	Debug bool

	// number of different drive-like body states (hunger, thirst, etc), that are satisfied by a corresponding positive US outcome -- this does not include the first curiosity drive
	NDrives int

	// number of negative US outcomes -- these are added after NDrives positive USs to total US list
	NNegUSs int

	// total number of USs = NDrives + NNegUSs
	NUSs int `edit:"-"`

	// number of different arms
	NArms int

	// maximum arm length (distance)
	MaxArmLength int

	// number of different CSs -- typically at least a unique CS per US -- relationship is determined in the US params
	NCSs int

	// parameters associated with each US.  The first NDrives are positive USs, and beyond that are negative USs
	USs []*USParams

	// state of each arm: dist, effort, US, CS
	Arms []*Arm

	// misc params
	Params Params `view:"add-fields"`
}

type Env struct {

	// name of environment -- Train or Test
	Nm string

	// our data parallel index
	Di int `edit:"-"`

	// configuration parameters
	Config Config

	// current drive strength for each of Config.NDrives in normalized 0-1 units of each drive: 0 = first sim drive, not curiosity
	Drives []float32

	// arm-wise location: either facing (Pos=0) or in (Pos > 0)
	Arm int `edit:"-"`

	// current position in the Arm: 0 = at start looking in, otherwise at given distance into the arm
	Pos int `edit:"-"`

	// current integer time step since last NewStart
	Tick int `edit:"-"`

	// current target drive, in paradigms where that is used (e.g., Approach)
	TrgDrive int `edit:"-"`

	// Current US being consumed -- is -1 unless being consumed
	USConsumed int `edit:"-"`

	// reward or punishment value generated by the current US being consumed -- just the Magnitude of the US -- does NOT include any modulation by Drive
	USValue float32 `edit:"-"`

	// just finished consuming a US -- ready to start doing something new
	JustConsumed bool `edit:"-"`

	// arm(s) with maximum Drive * Mag * Prob US outcomes
	ArmsMaxValue []int `edit:"-"`

	// maximum value for ArmsMaxValue arms
	MaxValue float32 `edit:"-"`

	// arm(s) with maximum Value outcome discounted by Effort
	ArmsMaxUtil []int `edit:"-"`

	// maximum utility for ArmsMaxUtil arms
	MaxUtil float32 `edit:"-"`

	// arm(s) with negative US outcomes
	ArmsNeg []int `edit:"-"`

	// last action taken
	LastAct Actions `edit:"-"`

	// effort on current trial
	Effort float32 `edit:"-"`

	// last CS seen
	LastCS int `edit:"-"`

	// last US -- previous trial
	LastUS int `edit:"-"`

	// just gated on this trial -- set by sim-- used for instinct
	JustGated bool `edit:"-"`

	// has gated at some point during sequence -- set by sim -- used for instinct
	HasGated bool `edit:"-"`

	// named states -- e.g., USs, CSs, etc
	States map[string]*etensor.Float32

	// maximum length of any arm
	MaxLength int `edit:"-"`

	// random number generator for the env -- all random calls must use this
	Rand erand.SysRand `view:"-"`

	// random seed
	RndSeed int64 `edit:"-"`
}

type GUI struct {

	// update display -- turn off to make it faster
	Disp bool

	// the env being visualized
	Env *Env

	// name of current env -- number is NData index
	EnvName string

	// 3D visualization of the Scene
	SceneView *xyzview.SceneView

	// 2D visualization of the Scene
	Scene2D *core.SVG

	// list of material colors
	MatColors []string

	// internal state colors
	StateColors map[string]string

	// thickness (X) and height (Y) of walls
	WallSize math32.Vector2

	// current internal / behavioral state
	State TraceStates

	// trace record of recent activity
	Trace StateTrace

	// view of the gui obj
	StructView *views.StructView `view:"-"`

	// ArmMaze TabView
	WorldTabs *core.Tabs `view:"-"`

	// ArmMaze is running
	IsRunning bool `view:"-"`

	// current depth map
	DepthValues []float32

	// offscreen render camera settings
	Camera evev.Camera

	// color map to use for rendering depth map
	DepthMap views.ColorMapName

	// first-person right-eye full field view
	EyeRFullImage *core.Image `view:"-"`

	// first-person right-eye fovea view
	EyeRFovImage *core.Image `view:"-"`

	// depth map bitmap view
	DepthImage *core.Image `view:"-"`

	// plot of positive valence drives, active OFC US state, and reward
	USposPlot *eplot.Plot2D

	// data for USPlot
	USposData *etable.Table

	// plot of negative valence active OFC US state, and outcomes
	USnegPlot *eplot.Plot2D

	// data for USPlot
	USnegData *etable.Table

	// geometry of world
	Geom Geom

	// world
	World *eve.Group

	// 3D view of world
	View3D *evev.View `view:"-"`

	// emer group
	Emery *eve.Group `view:"-"`

	// arms group
	Arms *eve.Group `view:"-"`

	// stims group
	Stims *eve.Group `view:"-"`

	// Right eye of emery
	EyeR eve.Body `view:"-"`

	// contacts from last step, for body
	Contacts eve.Contacts `view:"-"`
}

type Geom struct {

	// width of arm -- emery rodent is 1 unit wide
	ArmWidth float32 `default:"2"`

	// total space between arms, ends up being divided on either side
	ArmSpace float32 `default:"1"`

	// multiplier per unit arm length -- keep square with width
	LengthScale float32 `default:"2"`

	// thickness of walls, floor
	Thick float32 `default:"0.1"`

	// height of walls
	Height float32 `default:"0.2"`

	// width + space
	ArmWidthTot float32 `edit:"-"`

	// computed total depth, starts at 0 goes deep
	Depth float32 `edit:"-"`

	// computed total width
	Width float32 `edit:"-"`

	// half width for centering on 0 X
	HalfWidth float32 `edit:"-"`
}

type Paradigms int32 //enums:enum

type Params struct {

	// effort for turning
	TurnEffort minmax.F32 `nest:"+" default:"{'Min':0.5, 'Max':0.5}"`

	// effort for consuming US
	ConsumeEffort minmax.F32 `nest:"+" default:"{'Min':0.5, 'Max':0.5}"`

	// permute the order of CSs prior to applying them to arms -- having this off makes it easier to visually determine match between Drive and arm approach, and shouldn't make any difference to behavior (model doesn't know about this ordering).
	PermuteCSs bool `default:"false"`

	// after running down an Arm, a new random starting location is selected (otherwise same arm as last run)
	RandomStart bool `default:"true"`

	// if true, allow movement between arms just by going Left or Right -- otherwise once past the start, no switching is allowed
	OpenArms bool `default:"true"`

	// strength of inactive inputs (e.g., Drives in Approach paradigm)
	Inactive minmax.F32 `nest:"+" default:"{'Min':0, 'Max':0}" view:"inline"`

	// number of Y-axis repetitions of localist stimuli -- for redundancy in spiking nets
	NYReps int `default:"4"`
}

type StateTrace []*TraceRec

type TraceRec struct {

	// absolute time
	Time float32

	// trial counter
	Trial int

	// current arm
	Arm int

	// position in arm
	Pos int

	// behavioral / internal state summary
	State TraceStates

	// NDrives current drive state level
	Drives []float32
}

type TraceStates int32 //enums:enum

type USParams struct {

	// if true is a negative valence US -- these are after the first NDrives USs
	Negative bool

	// range of different magnitudes (uniformly sampled)
	Mag minmax.F32

	// probability of delivering the US
	Prob float32
}