def __init__(self, policy, start_state, **kwargs):
"""
Constructor for Agent base class
Parameters:
policy (Policy): defines the way this agent will behave. Must be a derived class of type Policy
start_state (list): starting state of this agent (must be valid based on WorldSpace inside Policy)
kwargs (dict):
ID (int): unique number to identify this agent in a multi-agent Game
is_training (bool): flag to track if the current agent is static or training
Returns:
Agent: A newly constructed Agent
"""
self._policy = policy
if self._policy.IsValidState(start_state):
self.curr_state = start_state
else:
ERROR(f"start_state [{start_state}] was invalid")
raise ValueError
if not isinstance(policy, Policy):
ERROR(f"policy must be of type {type(Policy)}, got [{type(policy)}]")
raise TypeError
self._id = kwargs.get("ID", np.random.randint(2**31-1))
self._is_training = kwargs.get("is_training", True)
def TrainAgent(self, id, episodes = None, steps_per_episode = None):
if episodes == None:
episodes = RLGame.DEFAULT_NUM_EPS
if steps_per_episode == None:
steps_per_episode = RLGame.DEFAULT_NUM_STEPS_PER_EP
try:
agent_to_train = self._agents[id]
except KeyError:
ERROR(f"Invalid key passed to StepAgent, {id} is not a valid agent id")
return False
for _, agent in self._agents.items():
if agent is agent_to_train:
agent.SetTrainable(True)
else:
agent.SetTrainable(False)
for ii in range(episodes):
INFO(f"Running episode {ii}")
steps, _ = self.RunEpisode(steps_per_episode)
INFO(f"Ran for {steps} steps")
INFO("Training complete")
def GetTargetEstimate(self, packet):
S_list, A_list, R_list = packet.Get()
try:
next_val = self.GetStateVal(S_list[1], A_list[1])
except IndexError as e:
ERROR(f"Bad ExpPacket sent to GetTargetEstimate. \nS_list and A_list must be at least length 2\nEach S,A pair must be valid. Got:\nS: {S_list}\nA: {A_list}")
raise IndexError
return R_list[0] + self.gamma*next_val
def StepAgentByID(self, id):
try:
agent = self._agents[id]
except KeyError:
ERROR(f"Invalid key passed to StepAgent, {id} is not a valid agent id")
return False
self._StepAgent(agent)
def convert_to_regexp(patterns):
"""Return list of regexp objects
"""
regexp_list = []
for pattern in patterns:
try:
regexp_list.append(re.compile(pattern, re.I))
except Exception:
ERROR("Invalid pattern: %s", pattern)
emergency_exit()
return regexp_list
def json_load(data, default=None, critical=False):
"""Load JSON from string or file
"""
try:
return (json.loads if not hasattr(data, 'read') else json.load)(data)
except ValueError:
if critical:
CRITICAL("Can't parse JSON data")
EXCEPTION("")
emergency_exit()
else:
ERROR("Can't parse JSON data")
return default
def json_dump(data, fhandler=None, critical=False, default=None):
"""Dump data to JSON and write to string or file
"""
try:
if fhandler:
json.dump(data, fhandler, indent=4)
else:
return json.dumps(data, indent=4)
except ValueError:
if critical:
CRITICAL("Can't dump data to JSON")
EXCEPTION("")
emergency_exit()
else:
ERROR("Can't dump data to JSON")
return default
except Exception, e:
ret["status"] = "Could not open the file: %s" % e
if f is not None:
ret["status"] = "Reading file..."
try:
ret["contents"] = f.read().decode(u'utf-8')
ret["status"] = "File has been read"
except Exception, e:
ret["status"] = "Could not read the file: %s" % e
if f is not None:
try:
f.close()
except Exception, e:
ERROR("Could not close the file: %s" % e)
return ret
def writeCode(code, library, filePath):
"""
Write the code to a given file.
@param code: the source code, as a big string
@param library: qname of the library
@param filePath: path of the filen to write
"""
f = None
def emergency_exit():
"""Immediately exit from script
"""
ERROR("Script terminated")
sys.exit(1)
def create_folder(path, erase=False, quiet=False):
"""Create folder at @path.
- @erase - erase existing folder
- @quiet - don't ask user about particular actions
- if @quiet is False, new folder with name @path[i]
will be created
- @erase has more priority than @quiet
"""
# >:( a lot of returns - not good style
DEBUG("Creating '%s' folder", path)
try:
os.makedirs(path)
except OSError as ex:
# we can't support other errors, except 'Folder already exists'
if ex.errno != 17:
CRITICAL("Can't create folder %s", path)
EXCEPTION("")
emergency_exit()
else:
DEBUG("Folder '%s' created", path)
return path
# Looks like folder already exists
# lets try to erase it or create new
# at different path
ERROR("Can't create '%s' folder", path)
if erase:
try:
erase_dir(path)
except Exception:
CRITICAL("Folder '%s' can't be erased")
else:
INFO("Folder erased: '{}'".format(path))
return path
# Well, erase == False or folder can't be erased
if not quiet:
answ = ''
while not answ:
answ = raw_input(("Type (E) to erase existing folder, "
"type (Q) to exit the script "
"or enter new folder name: ")).lower()
if answ == "e":
return create_folder(path, erase=True, quiet=quiet)
elif answ == "q":
script_exit()
elif answ:
return create_folder(answ, erase=False, quiet=quiet)
else:
return create_folder(find_unic_path(path), erase=erase, quiet=quiet)