tony/tensorneat-mend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

remove create_func....

Browse Source
This commit is contained in:
wls2002
2023-08-02 13:26:01 +08:00
parent 85318f98f3
commit 1499e062fe
34 changed files with 558 additions and 1022 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
algorithm/neat/ga/__init__.py
View File

@@ -1,2 +1,3 @@
from .crossover import crossover
from .mutate import create_mutate
from .mutate import mutate
from .operation import create_next_generation

4
algorithm/neat/ga/crossover.py
View File

@@ -9,7 +9,7 @@ def crossover(randkey, genome1: Genome, genome2: Genome):
use genome1 and genome2 to generate a new genome
notice that genome1 should have higher fitness than genome2 (genome1 is winner!)
"""
randkey_1, randkey_2, key= jax.random.split(randkey, 3)
randkey_1, randkey_2, key = jax.random.split(randkey, 3)
# crossover nodes
keys1, keys2 = genome1.nodes[:, 0], genome2.nodes[:, 0]
@@ -67,4 +67,4 @@ def crossover_gene(rand_key: Array, g1: Array, g2: Array) -> Array:
only gene with the same key will be crossover, thus don't need to consider change key
"""
r = jax.random.uniform(rand_key, shape=g1.shape)
return jnp.where(r > 0.5, g1, g2)
return jnp.where(r > 0.5, g1, g2)

221
algorithm/neat/ga/mutate.py
View File

@@ -1,4 +1,4 @@
from typing import Tuple, Type
from typing import Tuple
import jax
from jax import Array, numpy as jnp, vmap
@@ -8,144 +8,141 @@ from core import State, Gene, Genome
from utils import check_cycles, fetch_random, fetch_first, I_INT, unflatten_conns
def create_mutate(config: NeatConfig, gene_type: Type[Gene]):
def mutate(config: NeatConfig, gene: Gene, state: State, randkey, genome: Genome, new_node_key):
"""
Create function to mutate a single genome
Mutate a population of genomes
"""
k1, k2 = jax.random.split(randkey)
def mutate_structure(state: State, randkey, genome: Genome, new_node_key):
genome = mutate_structure(config, gene, state, k1, genome, new_node_key)
genome = mutate_values(gene, state, randkey, genome)
def mutate_add_node(key_, genome_: Genome):
i_key, o_key, idx = choice_connection_key(key_, genome_.conns)
def nothing():
return genome_
def successful_add_node():
# disable the connection
new_genome = genome_.update_conns(genome_.conns.at[idx, 2].set(False))
# add a new node
new_genome = new_genome.add_node(new_node_key, gene_type.new_node_attrs(state))
# add two new connections
new_genome = new_genome.add_conn(i_key, new_node_key, True, gene_type.new_conn_attrs(state))
new_genome = new_genome.add_conn(new_node_key, o_key, True, gene_type.new_conn_attrs(state))
return new_genome
# if from_idx == I_INT, that means no connection exist, do nothing
return jax.lax.cond(idx == I_INT, nothing, successful_add_node)
def mutate_delete_node(key_, genome_: Genome):
# TODO: Do we really need to delete a node?
# randomly choose a node
key, idx = choice_node_key(key_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=False, allow_output_keys=False)
def nothing():
return genome_
def successful_delete_node():
# delete the node
new_genome = genome_.delete_node_by_pos(idx)
# delete all connections
new_conns = jnp.where(((new_genome.conns[:, 0] == key) | (new_genome.conns[:, 1] == key))[:, None],
jnp.nan, new_genome.conns)
return new_genome.update_conns(new_conns)
return jax.lax.cond(idx == I_INT, nothing, successful_delete_node)
def mutate_add_conn(key_, genome_: Genome):
# randomly choose two nodes
k1_, k2_ = jax.random.split(key_, num=2)
i_key, from_idx = choice_node_key(k1_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=True, allow_output_keys=True)
o_key, to_idx = choice_node_key(k2_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=False, allow_output_keys=True)
conn_pos = fetch_first((genome_.conns[:, 0] == i_key) & (genome_.conns[:, 1] == o_key))
def nothing():
return genome_
def successful():
return genome_.add_conn(i_key, o_key, True, gene_type.new_conn_attrs(state))
def already_exist():
return genome_.update_conns(genome_.conns.at[conn_pos, 2].set(True))
return genome
is_already_exist = conn_pos != I_INT
def mutate_structure(config: NeatConfig, gene: Gene, state: State, randkey, genome: Genome, new_node_key):
def mutate_add_node(key_, genome_: Genome):
i_key, o_key, idx = choice_connection_key(key_, genome_.conns)
if config.network_type == 'feedforward':
u_cons = unflatten_conns(genome_.nodes, genome_.conns)
cons_exist = jnp.where(~jnp.isnan(u_cons[0, :, :]), True, False)
is_cycle = check_cycles(genome_.nodes, cons_exist, from_idx, to_idx)
def nothing():
return genome_
choice = jnp.where(is_already_exist, 0, jnp.where(is_cycle, 1, 2))
return jax.lax.switch(choice, [already_exist, nothing, successful])
def successful_add_node():
# disable the connection
new_genome = genome_.update_conns(genome_.conns.at[idx, 2].set(False))
elif config.network_type == 'recurrent':
return jax.lax.cond(is_already_exist, already_exist, successful)
# add a new node
new_genome = new_genome.add_node(new_node_key, gene.new_node_attrs(state))
else:
raise ValueError(f"Invalid network type: {config.network_type}")
# add two new connections
new_genome = new_genome.add_conn(i_key, new_node_key, True, gene.new_conn_attrs(state))
new_genome = new_genome.add_conn(new_node_key, o_key, True, gene.new_conn_attrs(state))
def mutate_delete_conn(key_, genome_: Genome):
# randomly choose a connection
i_key, o_key, idx = choice_connection_key(key_, genome_.conns)
return new_genome
def nothing():
return genome_
# if from_idx == I_INT, that means no connection exist, do nothing
return jax.lax.cond(idx == I_INT, nothing, successful_add_node)
def successfully_delete_connection():
return genome_.delete_conn_by_pos(idx)
def mutate_delete_node(key_, genome_: Genome):
# TODO: Do we really need to delete a node?
# randomly choose a node
key, idx = choice_node_key(key_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=False, allow_output_keys=False)
return jax.lax.cond(idx == I_INT, nothing, successfully_delete_connection)
def nothing():
return genome_
k1, k2, k3, k4 = jax.random.split(randkey, num=4)
r1, r2, r3, r4 = jax.random.uniform(k1, shape=(4,))
def successful_delete_node():
# delete the node
new_genome = genome_.delete_node_by_pos(idx)
def no(k, g):
return g
# delete all connections
new_conns = jnp.where(((new_genome.conns[:, 0] == key) | (new_genome.conns[:, 1] == key))[:, None],
jnp.nan, new_genome.conns)
genome = jax.lax.cond(r1 < config.node_add, mutate_add_node, no, k1, genome)
genome = jax.lax.cond(r2 < config.node_delete, mutate_delete_node, no, k2, genome)
genome = jax.lax.cond(r3 < config.conn_add, mutate_add_conn, no, k3, genome)
genome = jax.lax.cond(r4 < config.conn_delete, mutate_delete_conn, no, k4, genome)
return new_genome.update_conns(new_conns)
return genome
return jax.lax.cond(idx == I_INT, nothing, successful_delete_node)
def mutate_values(state: State, randkey, genome: Genome):
k1, k2 = jax.random.split(randkey, num=2)
nodes_keys = jax.random.split(k1, num=genome.nodes.shape[0])
conns_keys = jax.random.split(k2, num=genome.conns.shape[0])
def mutate_add_conn(key_, genome_: Genome):
# randomly choose two nodes
k1_, k2_ = jax.random.split(key_, num=2)
i_key, from_idx = choice_node_key(k1_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=True, allow_output_keys=True)
o_key, to_idx = choice_node_key(k2_, genome_.nodes, state.input_idx, state.output_idx,
allow_input_keys=False, allow_output_keys=True)
nodes_attrs, conns_attrs = genome.nodes[:, 1:], genome.conns[:, 3:]
conn_pos = fetch_first((genome_.conns[:, 0] == i_key) & (genome_.conns[:, 1] == o_key))
new_nodes_attrs = vmap(gene_type.mutate_node, in_axes=(None, 0, 0))(state, nodes_attrs, nodes_keys)
new_conns_attrs = vmap(gene_type.mutate_conn, in_axes=(None, 0, 0))(state, conns_attrs, conns_keys)
def nothing():
return genome_
# nan nodes not changed
new_nodes_attrs = jnp.where(jnp.isnan(nodes_attrs), jnp.nan, new_nodes_attrs)
new_conns_attrs = jnp.where(jnp.isnan(conns_attrs), jnp.nan, new_conns_attrs)
def successful():
return genome_.add_conn(i_key, o_key, True, gene.new_conn_attrs(state))
new_nodes = genome.nodes.at[:, 1:].set(new_nodes_attrs)
new_conns = genome.conns.at[:, 3:].set(new_conns_attrs)
def already_exist():
return genome_.update_conns(genome_.conns.at[conn_pos, 2].set(True))
return genome.update(new_nodes, new_conns)
is_already_exist = conn_pos != I_INT
def mutate(state, randkey, genome: Genome, new_node_key):
k1, k2 = jax.random.split(randkey)
if config.network_type == 'feedforward':
u_cons = unflatten_conns(genome_.nodes, genome_.conns)
cons_exist = jnp.where(~jnp.isnan(u_cons[0, :, :]), True, False)
is_cycle = check_cycles(genome_.nodes, cons_exist, from_idx, to_idx)
genome = mutate_structure(state, k1, genome, new_node_key)
genome = mutate_values(state, k2, genome)
choice = jnp.where(is_already_exist, 0, jnp.where(is_cycle, 1, 2))
return jax.lax.switch(choice, [already_exist, nothing, successful])
return genome
elif config.network_type == 'recurrent':
return jax.lax.cond(is_already_exist, already_exist, successful)
return mutate
else:
raise ValueError(f"Invalid network type: {config.network_type}")
def mutate_delete_conn(key_, genome_: Genome):
# randomly choose a connection
i_key, o_key, idx = choice_connection_key(key_, genome_.conns)
def nothing():
return genome_
def successfully_delete_connection():
return genome_.delete_conn_by_pos(idx)
return jax.lax.cond(idx == I_INT, nothing, successfully_delete_connection)
k1, k2, k3, k4 = jax.random.split(randkey, num=4)
r1, r2, r3, r4 = jax.random.uniform(k1, shape=(4,))
def no(k, g):
return g
genome = jax.lax.cond(r1 < config.node_add, mutate_add_node, no, k1, genome)
genome = jax.lax.cond(r2 < config.node_delete, mutate_delete_node, no, k2, genome)
genome = jax.lax.cond(r3 < config.conn_add, mutate_add_conn, no, k3, genome)
genome = jax.lax.cond(r4 < config.conn_delete, mutate_delete_conn, no, k4, genome)
return genome
def mutate_values(gene: Gene, state: State, randkey, genome: Genome):
k1, k2 = jax.random.split(randkey, num=2)
nodes_keys = jax.random.split(k1, num=genome.nodes.shape[0])
conns_keys = jax.random.split(k2, num=genome.conns.shape[0])
nodes_attrs, conns_attrs = genome.nodes[:, 1:], genome.conns[:, 3:]
new_nodes_attrs = vmap(gene.mutate_node, in_axes=(None, 0, 0))(state, nodes_keys, nodes_attrs)
new_conns_attrs = vmap(gene.mutate_conn, in_axes=(None, 0, 0))(state, conns_keys, conns_attrs)
# nan nodes not changed
new_nodes_attrs = jnp.where(jnp.isnan(nodes_attrs), jnp.nan, new_nodes_attrs)
new_conns_attrs = jnp.where(jnp.isnan(conns_attrs), jnp.nan, new_conns_attrs)
new_nodes = genome.nodes.at[:, 1:].set(new_nodes_attrs)
new_conns = genome.conns.at[:, 3:].set(new_conns_attrs)
return genome.update(new_nodes, new_conns)
def choice_node_key(rand_key: Array, nodes: Array,
@@ -186,4 +183,4 @@ def choice_connection_key(rand_key: Array, conns: Array):
i_key = jnp.where(idx != I_INT, conns[idx, 0], jnp.nan)
o_key = jnp.where(idx != I_INT, conns[idx, 1], jnp.nan)
return i_key, o_key, idx
return i_key, o_key, idx

40
algorithm/neat/ga/operation.py Normal file
View File

@@ -0,0 +1,40 @@
import jax
from jax import numpy as jnp, vmap
from config import NeatConfig
from core import Genome, State, Gene
from .mutate import mutate
from .crossover import crossover
def create_next_generation(config: NeatConfig, gene: Gene, state: State, randkey, winner, loser, elite_mask):
# prepare random keys
pop_size = state.idx2species.shape[0]
new_node_keys = jnp.arange(pop_size) + state.next_node_key
k1, k2 = jax.random.split(randkey, 2)
crossover_rand_keys = jax.random.split(k1, pop_size)
mutate_rand_keys = jax.random.split(k2, pop_size)
# batch crossover
wpn, wpc = state.pop_genomes.nodes[winner], state.pop_genomes.conns[winner]
lpn, lpc = state.pop_genomes.nodes[loser], state.pop_genomes.conns[loser]
n_genomes = vmap(crossover)(crossover_rand_keys, Genome(wpn, wpc), Genome(lpn, lpc))
# batch mutation
mutate_func = vmap(mutate, in_axes=(None, None, None, 0, 0, 0))
m_n_genomes = mutate_func(config, gene, state, mutate_rand_keys, n_genomes, new_node_keys) # mutate_new_pop_nodes
# elitism don't mutate
pop_nodes = jnp.where(elite_mask[:, None, None], n_genomes.nodes, m_n_genomes.nodes)
pop_conns = jnp.where(elite_mask[:, None, None], n_genomes.conns, m_n_genomes.conns)
# update next node key
all_nodes_keys = pop_nodes[:, :, 0]
max_node_key = jnp.max(jnp.where(jnp.isnan(all_nodes_keys), -jnp.inf, all_nodes_keys))
next_node_key = max_node_key + 1
return state.update(
pop_genomes=Genome(pop_nodes, pop_conns),
next_node_key=next_node_key,
)