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

complete fully stateful!

Browse Source 
use black to format all files!
This commit is contained in:
wls2002
2024-05-26 18:08:43 +08:00
parent cf69b916af
commit 18c3d44c79
41 changed files with 620 additions and 495 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tensorneat/examples/gymnax/arcbot.py
View File

@@ -5,7 +5,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -14,21 +14,23 @@ if __name__ == '__main__':
num_outputs=3,
max_nodes=50,
max_conns=100,
output_transform=lambda out: jnp.argmax(out) # the action of acrobot is {0, 1, 2}
output_transform=lambda out: jnp.argmax(
out
), # the action of acrobot is {0, 1, 2}
),
pop_size=10000,
species_size=10,
),
),
problem=GymNaxEnv(
env_name='Acrobot-v1',
env_name="Acrobot-v1",
),
generation_limit=10000,
fitness_target=-62
fitness_target=-62,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)

12
tensorneat/examples/gymnax/cartpole.py
View File

@@ -5,7 +5,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -14,21 +14,23 @@ if __name__ == '__main__':
num_outputs=2,
max_nodes=50,
max_conns=100,
output_transform=lambda out: jnp.argmax(out) # the action of cartpole is {0, 1}
output_transform=lambda out: jnp.argmax(
out
), # the action of cartpole is {0, 1}
),
pop_size=10000,
species_size=10,
),
),
problem=GymNaxEnv(
env_name='CartPole-v1',
env_name="CartPole-v1",
),
generation_limit=10000,
fitness_target=500
fitness_target=500,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)

29
tensorneat/examples/gymnax/cartpole_hyperneat.py
View File

@@ -10,11 +10,7 @@ from problem.rl_env import GymNaxConfig, GymNaxEnv
def example_conf():
return Config(
basic=BasicConfig(
seed=42,
fitness_target=500,
pop_size=10000
),
basic=BasicConfig(seed=42, fitness_target=500, pop_size=10000),
neat=NeatConfig(
inputs=4,
outputs=1,
@@ -23,28 +19,31 @@ def example_conf():
activation_default=Act.tanh,
activation_options=(Act.tanh,),
),
hyperneat=HyperNeatConfig(
activation=Act.sigmoid,
inputs=4,
outputs=2
),
hyperneat=HyperNeatConfig(activation=Act.sigmoid, inputs=4, outputs=2),
substrate=NormalSubstrateConfig(
input_coors=((-1, -1), (-0.5, -1), (0, -1), (0.5, -1), (1, -1)),
hidden_coors=(
# (-1, -0.5), (-0.5, -0.5), (0, -0.5), (0.5, -0.5),
(1, 0), (-1, 0), (-0.5, 0), (0, 0), (0.5, 0), (1, 0),
(1, 0),
(-1, 0),
(-0.5, 0),
(0, 0),
(0.5, 0),
(1, 0),
# (1, 0.5), (-1, 0.5), (-0.5, 0.5), (0, 0.5), (0.5, 0.5), (1, 0.5),
),
output_coors=((-1, 1), (1, 1)),
),
problem=GymNaxConfig(
env_name='CartPole-v1',
output_transform=lambda out: jnp.argmax(out) # the action of cartpole is {0, 1}
)
env_name="CartPole-v1",
output_transform=lambda out: jnp.argmax(
out
), # the action of cartpole is {0, 1}
),
)
if __name__ == '__main__':
if __name__ == "__main__":
conf = example_conf()
algorithm = HyperNEAT(conf, NormalGene, NormalSubstrate)

12
tensorneat/examples/gymnax/mountain_car.py
View File

@@ -5,7 +5,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -14,21 +14,23 @@ if __name__ == '__main__':
num_outputs=3,
max_nodes=50,
max_conns=100,
output_transform=lambda out: jnp.argmax(out) # the action of mountain car is {0, 1, 2}
output_transform=lambda out: jnp.argmax(
out
), # the action of mountain car is {0, 1, 2}
),
pop_size=10000,
species_size=10,
),
),
problem=GymNaxEnv(
env_name='MountainCar-v0',
env_name="MountainCar-v0",
),
generation_limit=10000,
fitness_target=0
fitness_target=0,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)

12
tensorneat/examples/gymnax/mountain_car_continuous.py
View File

@@ -4,7 +4,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
from utils import Act
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -14,23 +14,23 @@ if __name__ == '__main__':
max_nodes=50,
max_conns=100,
node_gene=DefaultNodeGene(
activation_options=(Act.tanh, ),
activation_options=(Act.tanh,),
activation_default=Act.tanh,
)
),
),
pop_size=10000,
species_size=10,
),
),
problem=GymNaxEnv(
env_name='MountainCarContinuous-v0',
env_name="MountainCarContinuous-v0",
),
generation_limit=10000,
fitness_target=500
fitness_target=500,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)

11
tensorneat/examples/gymnax/pendulum.py
View File

@@ -4,7 +4,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
from utils import Act
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -17,21 +17,22 @@ if __name__ == '__main__':
activation_options=(Act.tanh,),
activation_default=Act.tanh,
),
output_transform=lambda out: out * 2 # the action of pendulum is [-2, 2]
output_transform=lambda out: out
* 2, # the action of pendulum is [-2, 2]
),
pop_size=10000,
species_size=10,
),
),
problem=GymNaxEnv(
env_name='Pendulum-v1',
env_name="Pendulum-v1",
),
generation_limit=10000,
fitness_target=0
fitness_target=0,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)

8
tensorneat/examples/gymnax/reacher.py
View File

@@ -5,7 +5,7 @@ from algorithm.neat import *
from problem.rl_env import GymNaxEnv
if __name__ == '__main__':
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
@@ -20,14 +20,14 @@ if __name__ == '__main__':
),
),
problem=GymNaxEnv(
env_name='Reacher-misc',
env_name="Reacher-misc",
),
generation_limit=10000,
fitness_target =500
fitness_target=500,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)
state, best = pipeline.auto_run(state)