def calc_util(self, next_pos_idxs=None):
"""Calculate the utility of moving in any given direction."""
# set and use next pos idxs if they haven't been provided
if next_pos_idxs is None:
next_pos_idxs = self.get_next_pos_idxs()
# calculate utility for all moves
self.move_utils[:] = -np.inf
for move_ctr, next_pos_idx in enumerate(next_pos_idxs):
# leave at minimum if move idx is out of bounds
if self.env.idx_out_of_bounds(next_pos_idx):
continue
# get change in entropy if source found
deltaS_find_src = -self.S
# calculate expected change in entropy if source not found
# calculate probability of all possible odor sample values and
# change in src pos entropy resulting from each odor
odor_prob = np.zeros(self.odor_domain.shape, dtype=float)
deltaS = np.zeros(self.odor_domain.shape, dtype=float)
for odor_idx, odor in enumerate(self.odor_domain):
# get src prior, src like & src-odor joint
like = np.exp(self.get_loglike(odor, next_pos_idx))
joint = like * self.prob
# marginalize over src position to get odor prob
odor_prob[odor_idx] = np.sum(joint)
# calculate change in entropy of src pos distribution given
# this odor
next_prob = self.update_src_prob(odor,
next_pos_idx,
store=False,
log=False)
deltaS[odor_idx] = entropy(next_prob) - self.S
# calculate expected change in entropy if source not found
# (averaged over odors)
exptd_deltaS_no_src = np.dot(deltaS, odor_prob)
## calculate probability of finding source
pfind_src = self.prob[tuple(next_pos_idx)]
pno_src = 1 - pfind_src
# calculate final expected change in entropy
exptd_deltaS = exptd_deltaS_no_src * pno_src + deltaS_find_src * pfind_src
if np.isnan(exptd_deltaS):
print 'Error! Switching to debugging mode...'
import pdb
pdb.set_trace()
self.move_utils[move_ctr] = -exptd_deltaS
def calc_util(self, next_pos_idxs=None):
"""Calculate the utility of moving in any given direction."""
# set and use next pos idxs if they haven't been provided
if next_pos_idxs is None:
next_pos_idxs = self.get_next_pos_idxs()
# calculate utility for all moves
self.move_utils[:] = -np.inf
for move_ctr, next_pos_idx in enumerate(next_pos_idxs):
# leave at minimum if move idx is out of bounds
if self.env.idx_out_of_bounds(next_pos_idx):
continue
# get change in entropy if source found
deltaS_find_src = -self.S
# calculate expected change in entropy if source not found
# calculate probability of all possible odor sample values and
# change in src pos entropy resulting from each odor
odor_prob = np.zeros(self.odor_domain.shape, dtype=float)
deltaS = np.zeros(self.odor_domain.shape, dtype=float)
for odor_idx, odor in enumerate(self.odor_domain):
# get src prior, src like & src-odor joint
like = np.exp(self.get_loglike(odor, next_pos_idx))
joint = like * self.prob
# marginalize over src position to get odor prob
odor_prob[odor_idx] = np.sum(joint)
# calculate change in entropy of src pos distribution given
# this odor
next_prob = self.update_src_prob(odor, next_pos_idx,
store=False, log=False)
deltaS[odor_idx] = entropy(next_prob) - self.S
# calculate expected change in entropy if source not found
# (averaged over odors)
exptd_deltaS_no_src = np.dot(deltaS, odor_prob)
## calculate probability of finding source
pfind_src = self.prob[tuple(next_pos_idx)]
pno_src = 1 - pfind_src
# calculate final expected change in entropy
exptd_deltaS = exptd_deltaS_no_src*pno_src + deltaS_find_src*pfind_src
if np.isnan(exptd_deltaS):
print 'Error! Switching to debugging mode...'
import pdb; pdb.set_trace()
self.move_utils[move_ctr] = -exptd_deltaS
def update_src_prob(self, odor=None, pos_idx=None, store=True, log=True):
"""Update probability distribution over src pos.
Args:
store: set to True to store updated log source probability
log: set to True to calculate unnormalized log probability. If
False, then normalized probability will be returned (not log)."""
# if no odor or pos_idx provided, assume we're using the stored one
if odor is None:
odor = self.odor
if pos_idx is None:
pos_idx = self.pos_idx
# create unnormalized log posterior
logposterior = self.get_loglike(odor, pos_idx) + self.logprob
# set probability to zero (log to -inf) at insect's position
logposterior[tuple(pos_idx)] = -np.inf
# if all values are -np.inf, set them all to zero, otherwise translate
# so that max value is 0 to keep things within reasonable dyn. range
if np.all(np.isinf(logposterior) * (logposterior < 0)):
logposterior[:] = 0.
else:
logposterior -= logposterior.max()
# either store or return log src probability
if store:
self.logprob = logposterior
# store real probability and entropy
# calculate normalized probability
prob = np.exp(self.logprob)
# normalize
prob /= prob.sum()
self.prob = prob
self.S = entropy(prob)
else:
if log:
return logposterior
else:
# calculate normalized probability
prob = np.exp(logposterior)
# normalize
prob /= prob.sum()
return prob
def update_src_prob(self, odor=None, pos_idx=None, store=True, log=True):
"""Update probability distribution over src pos.
Args:
store: set to True to store updated log source probability
log: set to True to calculate unnormalized log probability. If
False, then normalized probability will be returned (not log)."""
# if no odor or pos_idx provided, assume we're using the stored one
if odor is None:
odor = self.odor
if pos_idx is None:
pos_idx = self.pos_idx
# create unnormalized log posterior
logposterior = self.get_loglike(odor, pos_idx) + self.logprob
# set probability to zero (log to -inf) at insect's position
logposterior[tuple(pos_idx)] = -np.inf
# if all values are -np.inf, set them all to zero, otherwise translate
# so that max value is 0 to keep things within reasonable dyn. range
if np.all(np.isinf(logposterior)*(logposterior < 0)):
logposterior[:] = 0.
else:
logposterior -= logposterior.max()
# either store or return log src probability
if store:
self.logprob = logposterior
# store real probability and entropy
# calculate normalized probability
prob = np.exp(self.logprob)
# normalize
prob /= prob.sum()
self.prob = prob
self.S = entropy(prob)
else:
if log:
return logposterior
else:
# calculate normalized probability
prob = np.exp(logposterior)
# normalize
prob /= prob.sum()
return prob
