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

update some examples

Browse Source
This commit is contained in:
root
2024-07-11 20:45:40 +08:00
parent cef27b56bb
commit e372ed7dcc
16 changed files with 152 additions and 2375 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
examples/brax/ant.py
View File

@@ -1,39 +0,0 @@
from pipeline import Pipeline
from algorithm.neat import *
from problem.rl_env import BraxEnv
from tensorneat.common import Act
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
genome=DefaultGenome(
num_inputs=27,
num_outputs=8,
max_nodes=100,
max_conns=200,
node_gene=DefaultNodeGene(
activation_options=(Act.tanh,),
activation_default=Act.tanh,
),
output_transform=Act.tanh,
),
pop_size=1000,
species_size=10,
compatibility_threshold=3.5,
survival_threshold=0.01,
),
),
problem=BraxEnv(
env_name="ant",
),
generation_limit=10000,
fitness_target=5000,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)

48
examples/brax/half_cheetah.py
View File

@@ -1,48 +0,0 @@
import jax
from pipeline import Pipeline
from algorithm.neat import *
from problem.rl_env import BraxEnv
from tensorneat.common import Act
def sample_policy(randkey, obs):
return jax.random.uniform(randkey, (6,), minval=-1, maxval=1)
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
genome=DefaultGenome(
num_inputs=17,
num_outputs=6,
max_nodes=50,
max_conns=100,
node_gene=DefaultNodeGene(
activation_options=(Act.tanh,),
activation_default=Act.tanh,
),
output_transform=Act.tanh,
),
pop_size=1000,
species_size=10,
),
),
problem=BraxEnv(
env_name="halfcheetah",
max_step=1000,
obs_normalization=True,
sample_episodes=1000,
sample_policy=sample_policy,
),
generation_limit=10000,
fitness_target=5000,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)

51
examples/brax/halfcheetah.py Normal file
View File

@@ -0,0 +1,51 @@
from tensorneat.pipeline import Pipeline
from tensorneat.algorithm.neat import NEAT
from tensorneat.genome import DefaultGenome, BiasNode
from tensorneat.problem.rl import BraxEnv
from tensorneat.common import Act, Agg
import jax
def random_sample_policy(randkey, obs):
return jax.random.uniform(randkey, (6,), minval=-1.0, maxval=1.0)
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
pop_size=1000,
species_size=20,
survival_threshold=0.1,
compatibility_threshold=1.0,
genome=DefaultGenome(
max_nodes=100,
max_conns=200,
num_inputs=17,
num_outputs=6,
init_hidden_layers=(),
node_gene=BiasNode(
activation_options=Act.tanh,
aggregation_options=Agg.sum,
),
output_transform=Act.standard_tanh,
),
),
problem=BraxEnv(
env_name="halfcheetah",
max_step=1000,
obs_normalization=True,
sample_episodes=1000,
sample_policy=random_sample_policy,
),
seed=42,
generation_limit=100,
fitness_target=8000,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)

37
examples/brax/reacher.py
View File

@@ -1,37 +0,0 @@
from pipeline import Pipeline
from algorithm.neat import *
from problem.rl_env import BraxEnv
from tensorneat.common import Act
if __name__ == "__main__":
pipeline = Pipeline(
algorithm=NEAT(
species=DefaultSpecies(
genome=DefaultGenome(
num_inputs=11,
num_outputs=2,
max_nodes=50,
max_conns=100,
node_gene=DefaultNodeGene(
activation_options=(Act.tanh,),
activation_default=Act.tanh,
),
output_transform=Act.tanh,
),
pop_size=100,
species_size=10,
),
),
problem=BraxEnv(
env_name="reacher",
),
generation_limit=10000,
fitness_target=5000,
)
# initialize state
state = pipeline.setup()
# print(state)
# run until terminate
state, best = pipeline.auto_run(state)

19
examples/brax/show_test.py
View File

@@ -1,19 +0,0 @@
import jax
from problem.rl_env import BraxEnv
def random_policy(randkey, forward_func, obs):
return jax.random.uniform(randkey, (6,), minval=-1, maxval=1)
if __name__ == "__main__":
problem = BraxEnv(env_name="walker2d", max_step=1000, action_policy=random_policy)
state = problem.setup()
randkey = jax.random.key(0)
problem.show(
state,
randkey,
act_func=lambda state, params, obs: obs,
params=None,
save_path="walker2d_random_policy",
)

2
examples/brax/walker2d.py
View File

@@ -9,7 +9,7 @@ import jax, jax.numpy as jnp
def random_sample_policy(randkey, obs):
return jax.random.uniform(randkey, (6,))
return jax.random.uniform(randkey, (6,), minval=-1.0, maxval=1.0)
if __name__ == "__main__":