her

type Agent struct {
	// Base for the agent.
	*agentv1.Base

	// Hyperparameters for the dqn+her agent.
	*Hyperparameters

	Policy       model.Model
	TargetPolicy model.Model
	Epsilon      common.Schedule
	// contains filtered or unexported fields
}

type AgentConfig struct {
	// Base for the agent.
	Base *agentv1.Base

	// Hyperparameters for the agent.
	*Hyperparameters

	// PolicyConfig for the agent.
	PolicyConfig *PolicyConfig

	// SuccessfulReward is the reward for reaching the goal.
	SuccessfulReward float32

	// MemorySize is the size of the memory.
	MemorySize int
}

type Event struct {
	*envv1.Outcome

	// State by which the action was taken.
	State *tensor.Dense

	// Goal the agent is trying to reach.
	Goal *tensor.Dense
	// contains filtered or unexported fields
}

type Events []*Event

type Hyperparameters struct {
	// Gamma is the discount factor (0≤γ≤1). It determines how much importance we want to give to future
	// rewards. A high value for the discount factor (close to 1) captures the long-term effective award, whereas,
	// a discount factor of 0 makes our agent consider only immediate reward, hence making it greedy.
	Gamma float32

	// Epsilon is the rate at which the agent should exploit vs explore.
	Epsilon common.Schedule

	// UpdateTargetEpisodes determines how often the target network updates its parameters.
	UpdateTargetEpisodes int
}

type LayerBuilder func(x, y *modelv1.Input) []layer.Config

type Memory struct {
	// contains filtered or unexported fields
}

type PolicyConfig struct {
	// Loss function to evaluate network performance.
	Loss modelv1.Loss

	// Optimizer to optimize the weights with regards to the error.
	Optimizer g.Solver

	// LayerBuilder is a builder of layer.
	LayerBuilder LayerBuilder

	// Batch size to train on.
	BatchSize int

	// Track is whether to track the model.
	Track bool
}