警告，这将是很长一段时间，因为我想尽可能具体。
确切的问题：这是一个多重处理问题。我确保我的类都按照之前实验中构建/预期的方式运行。
编辑：事先说过线程。
当我在线程环境中运行问题的玩具示例时，一切正常；然而，当我转向真正的问题时，代码就崩溃了。具体来说，我得到一个TypeError: can't pickle _thread.lock objects错误。完整堆栈位于底部。
我这里的线程需求与我改编代码的示例有点不同——https://github.com/CMA-ES/pycma/issues/31。在此示例中，我们有一个适应度函数，每次评估都可以独立调用该函数，并且所有函数调用都不能相互交互。然而，在我的实际问题中，我们正在尝试使用遗传算法来优化神经网络权重。遗传算法将建议潜在的权重，我们需要在我们的环境中评估这些神经网络控制器权重。在单线程情况下，我们只能有一个环境，在其中使用简单的 for 循环评估权重：[nn.evaluate(weights) for weights in potential_candidates]，找到表现最好的个体，并在下一轮突变中使用这些权重。然而，我们不能简单地在线程环境中进行一次模拟。
因此，我不是传递单个函数来评估，而是传递一个函数列表（每个人一个，其中环境相同，但我们已经分叉了进程，以便通信流不会在个体之间交互。 ）
还有一件事需要立即注意：
我正在使用整洁的并行评估数据结构
from clean.parallel import ParallelEvaluator # 使用 multiprocessing.Pool
玩具示例代码：
NPARAMS = nn.flat_init_weights.shape[0] # make this a 1000-dimensional problem.
NPOPULATION = 5 # use population size of 5.
MAX_ITERATION = 100 # run each solver for 100 function calls.
import time
from neat.parallel import ParallelEvaluator # uses multiprocessing.Pool
import cma
def fitness(x):
time.sleep(0.1)
return sum(x**2)
# # serial evaluation of all solutions
# def serial_evals(X, f=fitness, args=()):
# return [f(x, *args) for x in X]
# parallel evaluation of all solutions
def _evaluate2(self, weights, *args):
"""redefine evaluate without the dependencies on neat-internal data structures
"""
jobs = []
for i, w in enumerate(weights):
jobs.append(self.pool.apply_async(self.eval_function[i], (w, ) + args))
return [job.get() for job in jobs]
ParallelEvaluator.evaluate2 = _evaluate2
parallel_eval = ParallelEvaluator(12, [fitness]*NPOPULATION)
# time both
for eval_all in [parallel_eval.evaluate2]:
es = cma.CMAEvolutionStrategy(NPARAMS * [1], 1, {'maxiter': MAX_ITERATION,
'popsize': NPOPULATION})
es.disp_annotation()
while not es.stop():
X = es.ask()
es.tell(X, eval_all(X))
es.disp()
必要背景：
当我从玩具示例切换到真实代码时，上述操作失败了。
我的课程是：
LevelGenerator (simple GA class that implements mutate, etc)
GridGame (OpenAI wrapper; launches a Java server in which to run the simulation;
handles all communication between the Agent and the environment)
Agent (neural-network class, has an evaluate fn which uses the NN to play a single rollout)
Objective (handles serializing/de-serializing weights: numpy <--> torch; launching the evaluate function)
# The classes get composed to get the necessary behavior:
env = GridGame(Generator)
agent = NNAgent(env) # NNAgent is a subclass of (Random) Agent)
obj = PyTorchObjective(agent)
# My code normally all interacts like this in the single-threaded case:
def test_solver(solver): # Solver: CMA-ES, Differential Evolution, EvolutionStrategy, etc
history = []
for j in range(MAX_ITERATION):
solutions = solver.ask() #2d-numpy array. (POPSIZE x NPARAMS)
fitness_list = np.zeros(solver.popsize)
for i in range(solver.popsize):
fitness_list[i] = obj.function(solutions[i], len(solutions[i]))
solver.tell(fitness_list)
result = solver.result() # first element is the best solution, second element is the best fitness
history.append(result[1])
scores[j] = fitness_list
return history, result
所以，当我尝试运行时：
NPARAMS = nn.flat_init_weights.shape[0]
NPOPULATION = 5
MAX_ITERATION = 100
_x = NNAgent(GridGame(Generator))
gyms = [_x.mutate(0.0) for _ in range(NPOPULATION)]
objs = [PyTorchObjective(a) for a in gyms]
def evaluate(objective, weights):
return objective.fun(weights, len(weights))
import time
from neat.parallel import ParallelEvaluator # uses multiprocessing.Pool
import cma
def fitness(agent):
return agent.evalute()
# # serial evaluation of all solutions
# def serial_evals(X, f=fitness, args=()):
# return [f(x, *args) for x in X]
# parallel evaluation of all solutions
def _evaluate2(self, X, *args):
"""redefine evaluate without the dependencies on neat-internal data structures
"""
jobs = []
for i, x in enumerate(X):
jobs.append(self.pool.apply_async(self.eval_function[i], (x, ) + args))
return [job.get() for job in jobs]
ParallelEvaluator.evaluate2 = _evaluate2
parallel_eval = ParallelEvaluator(12, [obj.fun for obj in objs])
# obj.fun takes in the candidate weights, loads them into the NN, and then evaluates the NN in the environment.
# time both
for eval_all in [parallel_eval.evaluate2]:
es = cma.CMAEvolutionStrategy(NPARAMS * [1], 1, {'maxiter': MAX_ITERATION,
'popsize': NPOPULATION})
es.disp_annotation()
while not es.stop():
X = es.ask()
es.tell(X, eval_all(X, NPARAMS))
es.disp()
我收到以下错误：
TypeError Traceback (most recent call last)
<ipython-input-57-3e6b7bf6f83a> in <module>
6 while not es.stop():
7 X = es.ask()
----> 8 es.tell(X, eval_all(X, NPARAMS))
9 es.disp()
<ipython-input-55-2182743d6306> in _evaluate2(self, X, *args)
14 jobs.append(self.pool.apply_async(self.eval_function[i], (x, ) + args))
15
---> 16 return [job.get() for job in jobs]
<ipython-input-55-2182743d6306> in <listcomp>(.0)
14 jobs.append(self.pool.apply_async(self.eval_function[i], (x, ) + args))
15
---> 16 return [job.get() for job in jobs]
~/miniconda3/envs/thesis/lib/python3.7/multiprocessing/pool.py in get(self, timeout)
655 return self._value
656 else:
--> 657 raise self._value
658
659 def _set(self, i, obj):
~/miniconda3/envs/thesis/lib/python3.7/multiprocessing/pool.py in _handle_tasks(taskqueue, put, outqueue, pool, cache)
429 break
430 try:
--> 431 put(task)
432 except Exception as e:
433 job, idx = task[:2]
~/miniconda3/envs/thesis/lib/python3.7/multiprocessing/connection.py in send(self, obj)
204 self._check_closed()
205 self._check_writable()
--> 206 self._send_bytes(_ForkingPickler.dumps(obj))
207
208 def recv_bytes(self, maxlength=None):
~/miniconda3/envs/thesis/lib/python3.7/multiprocessing/reduction.py in dumps(cls, obj, protocol)
49 def dumps(cls, obj, protocol=None):
50 buf = io.BytesIO()
---> 51 cls(buf, protocol).dump(obj)
52 return buf.getbuffer()
53
TypeError: can't pickle _thread.lock objects
我还在这里读到，这可能是由于这是一个类函数这一事实引起的——类型错误：无法 pickle _thread.lock 对象——所以我创建了全局范围的适应度函数def fitness(agent): return agent.evalute()，但这也不起作用。
我认为这个错误可能是因为最初我在 PyTorchObjective 类中将评估函数作为 lambda 函数，但当我更改它时它仍然崩溃。
任何见解都将不胜感激，并感谢您阅读这面巨大的文字墙。
