dacbench.envs.onell_env

Module Contents

Classes

BinaryProblem

An abstract class for an individual in binary representation

OneMax

An individual for OneMax problem

LeadingOne

An individual for LeadingOne problem

OneLLEnv

Environment for (1+(lbd, lbd))-GA
class dacbench.envs.onell_env.BinaryProblem(n, val=None, rng=np.random.default_rng())

An abstract class for an individual in binary representation

is_optimal(self)
get_optimal(self)
eval(self)
abstract get_fitness_change_after_mutation(self, locs)

Calculate the change in fitness after flipping the bits at positions locs

Parameters

locs (1d-array) – positions where bits are flipped

objective after mutation - objective before mutation

abstract get_fitness_after_crossover(self, xprime, locs_x, locs_xprime)

Calculate fitness of the child when crossover with xprime, without doing the actual crossover

Parameters

  • xprime (1d boolean array) – the individual to crossover with

  • locs_x (1d boolean/integer array) – positions where we keep current bits of self

  • locs_xprime (: 1d boolean/integer array) – positions where we change to xprime’s bits

fitness of the new individual after crossover

mutate(self, p, n_offsprings, rng=np.random.default_rng())

Draw l ~ binomial(n, p), l>0 Generate n_offsprings children by flipping exactly l bits and select the best one

Parameters

  • p (float) – mutation probability, in range of [0,1]

  • n_offsprings (int) – number of mutated children

Returns

Return type

the best child (maximum fitness), its fitness and number of evaluations used

crossover(self, xprime, p, n_offsprings, include_xprime=True, count_different_inds_only=True, rng=np.random.default_rng())
Generate n_offsprings children using crossover on self and xprime, and return the best one

Crossover operator: for each bit, taking value from xprime with probability p and from self with probability 1-p

Parameters

  • xprime (1d boolean numpy array) – the individual to crossover with

  • p (float) – crossover bias, in range of [0,1]

  • include_xprime (boolean) – if True, include xprime in the selection for the best individual after all crossovers

  • count_different_inds_only (boolean) – if True, only count an evaluation of a child if it is different from both of its parents (self and xprime)

  • rng (numpy random generator) –

Returns

Return type

the best child (maximum fitness), its fitness and number of evaluations used

class dacbench.envs.onell_env.OneMax(n, val=None, rng=np.random.default_rng())

Bases: dacbench.envs.onell_env.BinaryProblem

An individual for OneMax problem The aim is to maximise the number of 1 bits

eval(self)
is_optimal(self)
get_optimal(self)
get_fitness_change_after_mutation(self, locs)

Calculate the change in fitness after flipping the bits at positions locs

Parameters

locs (1d-array) – positions where bits are flipped

objective after mutation - objective before mutation

get_fitness_after_crossover(self, xprime, locs_x, locs_xprime)

Calculate fitness of the child when crossover with xprime, without doing the actual crossover

Parameters

  • xprime (1d boolean array) – the individual to crossover with

  • locs_x (1d boolean/integer array) – positions where we keep current bits of self

  • locs_xprime (: 1d boolean/integer array) – positions where we change to xprime’s bits

fitness of the new individual after crossover

class dacbench.envs.onell_env.LeadingOne(n, val=None, rng=np.random.default_rng())

Bases: dacbench.envs.onell_env.BinaryProblem

An individual for LeadingOne problem The aim is to maximise the number of leading (and consecutive) 1 bits in the string

eval(self)
is_optimal(self)
get_optimal(self)
get_fitness_change_after_mutation(self, locs)

Calculate the change in fitness after flipping the bits at positions locs

Parameters

locs (1d-array) – positions where bits are flipped

objective after mutation - objective before mutation

get_fitness_after_crossover(self, xprime, locs_x, locs_xprime)

this implementation should be improved

dacbench.envs.onell_env.HISTORY_LENGTH = 5
class dacbench.envs.onell_env.OneLLEnv(config)

Bases: dacbench.AbstractEnv

Environment for (1+(lbd, lbd))-GA for both OneMax and LeadingOne problems

reset(self)

Resets env

Returns

Environment state

Return type

numpy.array

get_state(self)
get_onell_params(self, action)

Get OneLL-GA parameters (lbd1, lbd2, p and c) from an action

Returns: lbd1, lbd2, p, c
lbd1: float (will be converted to int in step())

number of mutated off-springs: in range [1,n]

lbd2: float (will be converted to int in step())

number of crossovered off-springs: in range [1,n]

p: float

mutation probability

c: float

crossover bias

step(self, action)

Execute environment step

Parameters

action (Box) – action to execute

Returns

  • state, reward, done, info

  • np.array, float, bool, dict

plot_agent_prediction(self, agent, dirname)

Plot agent progress for this particular environment

close(self) → bool

Close Env

No additional cleanup necessary

Returns

Closing confirmation

Return type

bool