资 源 简 介
LibPG
The PG library was intended to be a high-performance policy-gradient
reinforcement learning library. Since the first version it has been
extended to a number of value based RL algorithms, so the name is only
historical. It is now a general RL library which implements, for example, natural actor critic, and least squares policy iteration. It has been designed with
large distributed RL systems in mind. It"s not perfect, but it is
pretty fast. API documentation and examples are provided.
What libpg does NOT provide is model based planning algorithms such as
value iteration, or real-time dynamic programming, or exact policy
gradient. There is limited support for belief state tracking in the
simulators/Cassandra/ directory (named because we use the POMDP file
format created by Anthony Cassandra). One day I"d like to extend it
to these situations, but that will require some uptake of the library.
Project goals
Provide easy to use imple
文 件 列 表
libpg
Approximator.hh
BasicController.cc
BasicController.hh
Bias.cc
Bias.hh
BinaryController.cc
BinaryController.hh
CatObsActionTransform.cc
CatObsActionTransform.hh
configure
Controller.hh
CyclicPolicyBias.cc
CyclicPolicyBias.hh
docs
eGreedyPolicy.cc
eGreedyPolicy.hh
exclude_from_tar.txt
FactoredApproximator.cc
FactoredApproximator.hh
FactoredApproximatorMinUpdates.cc
FactoredApproximatorMinUpdates.hh
FactoredController.cc
FactoredController.hh
GOALPomdp.cc
GOALPomdp.hh
GPomdp.cc
GPomdp.hh
HardLimitTransform.cc
HardLimitTransform.hh
HMMTransform.cc
HMMTransform.hh
ImportanceSamplingController.cc
ImportanceSamplingController.hh
LineSearchAlg.cc
LineSearchAlg.hh
LookupTable.cc
LookupTable.hh
LookupTableBatch.cc
LookupTableBatch.hh
LSTDQController.cc
LSTDQController.hh
Makefile.default
MPL-1.1.txt
MultidimensionalLookupTable.cc
MultidimensionalLookupTable.hh
NACTransform.cc
NACTransform.hh
NeuralNet.cc
NeuralNet.hh
NeuralNetAtlas.cc
NeuralNetAtlas.hh
NeuralNetBatch.cc
NeuralNetBatch.hh
Observation.cc
Observation.hh
ObsWindowTransform.cc
ObsWindowTransform.hh
OLPomdp.cc
OLPomdp.hh
PGBasics.hh
Policy.hh
PSRTransform.cc
PSRTransform.hh
QLearningController.cc
QLearningController.hh
README.txt
RegressionController.cc
RegressionController.hh
RegularizeTransform.cc
RegularizeTransform.hh
RLAlg.cc
RLAlg.hh
Sampler.cc
Sampler.hh
SARSAController.cc
SARSAController.hh
Simulator.hh
simulators
SoftmaxPolicy.cc
SoftmaxPolicy.hh
Teacher.hh
tests
TransformApproximator.cc
TransformApproximator.hh
TransformController.cc
TransformController.hh
UBlasExtras.cc
UBlasExtras.hh
utils
ValueController.hh
