BibSonomy
::
user
::
idsia
::
tag
user
group
author
concept
BibTeX key
search:all
search:idsia
A blue social bookmark and publication sharing system.
tags
·
relations
·
groups
·
popular
help
·
blog
·
about
username:
password:
login
·
register
bookmarks
bookmarks per page:
5
10
20
50
100
publications
(1)
<<
< 1 >
>>
Policy Gradient Critics
Daan
Wierstra
and Jürgen
Schmidhuber
(
2007
)
to
actor-critic,
action\_selection,
policy\_gradient
by
idsia
and
2 other people
on Mar 11, 2008, 2:52 PM
URL
|
BibTeX
<<
< 1 >
>>
publications per page:
5
10
20
50
100
actor-critic, action\_selection,
as tag from all users
actor-critic, action\_selection,
as concept from idsia
actor-critic, action\_selection,
as concept from all users
related tags
+
policy\_gradient
relations
tags
action\_selection,
actor-critic,
adaptive,
adversary,
advice,
agents,
algorithm,
algorithm-portfolios,
algorithm-selection,
algorithmic,
algorithms,
alphabet,
and,
approach,
artificial,
asymptotic,
bandits,
basic,
bayes,
bayesian,
bernoulli,
bibtex-import,
bibtex-import-wt,
bounds,
cec2005,
class,
classes,
classification,
classifier,
clauses,
codingpopulation,
codingspike,
cognitive,
columnsreview,
complexity,
computability,
computation,
computational,
computations,
concepts,
conceptual,
conditional,
connectionsassociative,
consistency,
convergence,
correlated,
credible,
criteria,
cross,
crossover,
daanbib
daanbib,
data,
dblp
decent,
deceptive,
decision,
deficiency,
deletion,
density,
dependence,
description,
detection,
deterministic,
direct,
dirichlet,
discrete,
distribution,
distributions,
diversity,
entropy,
enumerable,
environment,
environments,
error,
estimation,
evaluation,
evolution,
evolutionary
evolutionary,
exact,
expectation,
expected,
experimental,
expert,
experts,
feature,
filter,
filters,
fitness,
follow,
function,
future,
game,
gas,
general,
genetic,
genotype-phenotype,
gestaltsubordinate,
gradient,
gradients,
graphical,
groupingsegmentation,
growing,
hayek,
hierarchy,
high,
image,
imported
imprecise,
inaki
induction,
inference,
infinite,
information,
intelligence,
interactionscrf,
intervals,
invariance,
juergen
juergen,
kolmogorov,
l-systems,
landscapes,
lateral,
leader,
leaning,
learning,
learningconnectionism,
learningmodel,
length,
lindenmayer,
linear,
linguistics,
local,
loss,
machine,
mapping,
marginalization,
martin-loef,
martin-lof,
mdl,
methodology,
minimal,
minimum,
missing,
mixture,
model,
models,
monotone,
motion,
multimodal,
mutual,
naive,
neural,
neutrality,
nlp,
nn
nn,
no-free-lunch,
non-parametric,
observable,
observation,
of,
online,
optima,
optimality,
optimization,
order,
paper,
parallel-computing,
parsing,
partial,
pedagogy,
perceptiondevelopment,
perturbed,
philosophy,
planning,
policy
policy,
policy\_gradient
polya,
poster,
posterior,
prediction,
preserve,
principles,
prior,
probabilities,
probability,
problems,
processingparsingsemanticscase,
programming
programming,
quasimeasures,
randomness,
rate
rate,
rational,
recombination,
redundancy,
regression,
reinforcement,
responsive,
restart
retrieval,
robotics
robust,
roles,
rule
scale,
schemes,
search
second,
selection,
self-adaptation,
self-optimizingness,
selfadaptation
selfadaptation,
semantics
semimeasure,
sentence
sequence
sequence,
sequential,
sokoban
solomonoff,
solomonoffs,
somormodel
spanning,
stabilization,
statistics,
strategy,
subsymbolic
system
systemface,
systemmaemodel,
systemmaereview,
test
the,
theorem
theory
theory,
time,
timing
total
tree
treebank
trees
uniform
universal
universal,
variance
video
visual
weights,
with
working