Data Structures

Here are the data structures with brief descriptions:

[detail level 12345]

▼Nrlpack	Implementation of RL Algorithms built on top of PyTorch
▼N_C	This package implements the classes to interface between C++ and Python
▼Ngrad_accumulator
CGradAccumulator	This class provides the python interface to C_GradAccumulator, the C++ class which performs heavier workloads
▼Nmemory
CMemory	This class provides the python interface to C_Memory, the C++ class which performs heavier workloads
▼Nactor_critic	This package implements the Actor-Critic methods
▼Na2c
CA2C	The A2C class implements the synchronous Actor-Critic method
▼Na3c
CA3C	The A2C class implements the synchronous Actor-Critic method
▼Ndqn	This package implements the DQN methods
▼Ndqn
CDqn	This is a helper class that selects the correct the variant of DQN implementations based on prioritization strategy determined by the argument prioritization_params
▼Ndqn_agent
CDqnAgent	This class implements the basic DQN methodology, i.e
▼Ndqn_proportional_prioritization_agent
CDqnProportionalPrioritizationAgent	This class implements the DQN with Proportional prioritization strategy
▼Ndqn_rank_based_prioritization_agent
CDqnRankBasedPrioritizationAgent	This class implements the DQN with Rank-Based prioritization strategy
▼Nenvironments	This package implements the gym environment to couple it with selected environment
▼Nenvironments
CEnvironments	This class is a generic class to train any agent in any environment
▼Nmodels	This package implements the in-built models
▼N_mlp_feature_extractor
C_MlpFeatureExtractor	This class is a PyTorch Model implementing the MLP based feature extractor for 1-D or 2-D state values
▼Nactor_critic_mlp_policy
CActorCriticMlpPolicy	This class is a PyTorch Model implementing the MLP based Actor-Critic Policy
▼Nmlp
CMlp	This class is a PyTorch Model implementing the MLP model for 1-D or 2-D state values
▼Nsimulator
CSimulator	Simulator class simulates the environments and runs the agent through the environment
▼Nsimulator_distributed
CSimulatorDistributed	Similar to rlpack.simulator.Simulator, SimulatorDistributed class sets up agents and runs simulation by interacting with the given environment
▼Nutils	This package implements the basic utilities to be used across rlpack
▼Nbase	This package implements the base classes to be used across rlpack
▼Nagent
CAgent	The base class for all agents
▼Ninternal_code_register
CInternalCodeRegister
▼Nregister
CRegister	This abstract class contains all the necessary information about agents and models for setting them up
▼Ninternal_code_setup
CInternalCodeSetup
▼Nnormalization
CNormalization	Normalization class providing methods for normalization techniques
▼Nsanity_check
CSanityCheck	This class does the basic sanity check of input_config
▼Nsetup
CSetup	This class sets up all the necessary objects that are required to run any configuration
CC_GradAccumulator
▼CC_Memory	The class C_Memory is the C++ backend for memory-buffer used in algorithms that stores transitions in a buffer. This class contains optimized routines to support Python front-end of rlpack._C.memory.Memory class
CC_MemoryData	The class C_MemoryData keeps the references to data that is associated with C_Memory. This class implements the functions necessary to retrieve the data by de-referencing the data associated with C_Memory
COffload	Template Offload class for CPU with CPU optimized OpenMP routines
CSumTree	The class SumTree is a class which represents the Sum-Tree which is used in proportional prioritization. It implements all the methods necessary to create the Sum-Tree and sample from it
CSumTreeNode	The class SumTreeNode is a private class which represents a node in Sum-Tree. This is only used when we use proportional prioritization