def make_net(genome, config, bs):
#start by setting up a substrate for this bad cartpole boi
input_cords, output_cords, leaf_names = set_initial_coords()
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, PARAMS)
network = net_builder.create_phenotype_network_nd()
return network
def reset_substrate(states):
input_cords = []
output_cords = [(0.0, -1.0, 0.0)]
sign = -1
for i in range(4):
input_cords.append((0.0, 0.0, 0.0 + (states[i] / 10)))
return Substrate(input_cords, output_cords)
def make_net(genome, config, bs):
#start by setting up a substrate for this bad cartpole boi
params = {"initial_depth": 2,
"max_depth": 4,
"variance_threshold": 0.00013,
"band_threshold": 0.00013,
"iteration_level": 3,
"division_threshold": 0.00013,
"max_weight": 3.0,
"activation": "tanh"}
input_cords = []
output_cords = [(0.0, -1.0, 0.0)]
sign = 1
for i in range(4):
input_cords.append((0.0 - i/10*sign, 1.0, 0.0))
sign *= -1
leaf_names = []
for i in range(3):
leaf_names.append('leaf_one_'+str(i))
leaf_names.append('leaf_two_'+str(i))
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
# print(cppn)
print(leaf_names)
print(config.genome_config.input_keys)
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, params)
net = net_builder.create_phenotype_network_nd()
return net
def make_net(genome, config, bs):
#start by setting up a substrate for this bad cartpole boi
params = {
"initial_depth": 2,
"max_depth": 4,
"variance_threshold": 0.8,
"band_threshold": 0.05,
"iteration_level": 3,
"division_threshold": 0.3,
"max_weight": 34.0,
"activation": "sigmoid"
}
input_cords = []
output_cords = [(0.0, -1.0, -1.0)]
sign = 1
# we will use a 3 dimensional substrate, coords laid out here
for i in range(4):
input_cords.append((0.0 - i / 10 * sign, 0.0, 0.0))
sign *= -1
leaf_names = []
for i in range(len(output_cords[0])):
leaf_names.append(str(i) + "_in")
leaf_names.append(str(i) + "_out")
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, params)
net = net_builder.create_phenotype_network_nd()
return net
def reset_substrate(states):
input_cords = []
output_cords = [(0.0, -1.0, -1.0)]
sign = -1
for i in range(4):
input_cords.append((0.0 - i/10*sign, 0.0, states[i]/100.))
sign *= -1
return Substrate(input_cords, output_cords)
def reset_substrate(self, input_row):
current_inputs = self.substrate.input_coordinates
new_input = []
for ix,t in enumerate(current_inputs):
t = list(t)
offset = input_row[ix] * .5
t[2] = t[2] + .5
new_input.append(tuple(t))
#self.in_shapes = new_input
self.substrate = Substrate(new_input, self.out_shapes)
def execute_back_prop(genome_dict, champ_key, config):
input_cords, output_cords, leaf_names = set_initial_coords()
[cppn] = create_cppn(genome_dict[champ_key], config, leaf_names,
['cppn_out'])
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, PARAMS)
champ_output = net_builder.safe_baseline(False)
for key in genome_dict:
if key != champ_key:
[cppn_2] = create_cppn(genome_dict[key], config, leaf_names,
['cppn_out'])
es_net = ESNetwork(Substrate(input_cords, output_cords), cppn_2,
PARAMS)
output = es_net.safe_baseline(True)
es_net.optimizer.zero_grad()
if output.requires_grad == True:
loss_val = (champ_output - output).pow(2).mean()
loss_val.backward()
es_net.optimizer.step()
es_net.map_back_to_genome(genome_dict[key], config, leaf_names,
['cppn_out'])
else:
print("error less fit has no grad attached")
return
def refresh(self):
self.in_shapes = []
self.out_shapes = [(0.0, -1.0, -1.0)]
self.hs = HistWorker()
self.hs.get_binance_train()
print(self.hs.currentHists.keys())
self.end_idx = len(self.hs.hist_shaped[0])
self.but_target = .1
print(self.hs.hist_shaped.shape)
self.num_syms = self.hs.hist_shaped.shape[0]
self.inputs = self.hs.hist_shaped[0].shape[1] + 1
self.outputs = 1
sign = 1
for ix2 in range(1,self.inputs+1):
sign *= -1
self.in_shapes.append((0.0+(sign*.01*ix2), 0.0-(sign*.01*ix2), 0.0))
self.substrate = Substrate(self.in_shapes, self.out_shapes)
self.set_leaf_names()
def make_net(genome,
config,
batch_size,
state_space_dim=111,
action_space_dim=8) -> RecurrentNet:
#start by setting up a substrate for this bad ant boi
params = {
"initial_depth": 1,
"max_depth": 5,
"variance_threshold": 0.8,
"band_threshold": 0.05,
"iteration_level": 3,
"division_threshold": 0.3,
"max_weight": 10.0,
"activation": "relu"
}
assert params[
"activation"] in piecewise_linear_activations, f"for NAS without search, network activation needs to be piecewise linear"
# FIXME this can just be list
joint_name_dict = {
0: "hip_4",
1: "ankle_4",
2: "hip_1",
3: "ankle_1",
4: "hip_2",
5: "ankle_2",
6: "hip_3",
7: "ankle_3",
}
assert len(joint_name_dict) == len(output_coords)
leaf_names = []
for i in range(len(output_coords[0])):
leaf_names.append(str(i) + "_in")
leaf_names.append(str(i) + "_out")
input_coords = get_in_coords()
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
net_builder = ESNetwork(Substrate(input_coords, output_coords), cppn,
params)
net = net_builder.create_phenotype_network_nd(batch_size=batch_size)
return net # RecurrentNet ((not necessarily actually recurrent))
def make_net(genome, config, _batch_size):
params = {
"initial_depth": 1,
"max_depth": 2,
"variance_threshold": 0.8,
"band_threshold": 0.05,
"iteration_level": 3,
"division_threshold": 0.3,
"max_weight": 30.0,
"activation": "tanh"
}
input_cords = [(-1.0, 1.0, 0.0), (-.5, 1.0, 0.0), (.5, 1.0, 0.0),
(1.0, 1.0, 0.0)]
output_cords = [(-1.0, -1.0, -1.0), (0.0, -1.0, -1.0), (1.0, -1.0, -1.0)]
leaf_names = []
for i in range(len(output_cords[0])):
leaf_names.append(str(i) + "_in")
leaf_names.append(str(i) + "_out")
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, params)
#net = net_builder.create_phenotype_network_nd('./genome_vis')
return net_builder
def make_net(genome, config, bs):
#start by setting up a substrate for this bad cartpole boi
params = {
"initial_depth": 1,
"max_depth": 2,
"variance_threshold": 0.8,
"band_threshold": 0.13,
"iteration_level": 3,
"division_threshold": 0.3,
"max_weight": 3.0,
"activation": "relu"
}
input_cords = [(0.1, 0.1, 0.1), (-0.1, -0.1, -0.1)]
output_cords = [(0.0, 1.0, -1.0), (0.0, 0.0, -1.0), (0.0, -1.0, -1.0)]
leaf_names = []
for i in range(len(output_cords[0])):
leaf_names.append(str(i) + "_in")
leaf_names.append(str(i) + "_out")
[cppn] = create_cppn(genome, config, leaf_names, ['cppn_out'])
net_builder = ESNetwork(Substrate(input_cords, output_cords), cppn, params)
net = net_builder.create_phenotype_network_nd('./genome_vis')
return net
def reset_substrate(states):
input_coords = get_in_coords(states)
return Substrate(input_coords, output_coords)