Data used to construct an IRLTrainer instance More...
#include <RLTrainer.h>
Inheritance diagram for SmartEngine::RLTrainerCInfo:
Public Attributes | |
| IContext * | context = nullptr |
| The context to perform graph operations within. More... | |
| IAgentDataStore * | dataStore = nullptr |
| The data store used to save experience state More... | |
| const char * | agentName = "" |
| Should be a unique name across the data store More... | |
| const char ** | policyNodeNames = nullptr |
| The names of the output nodes of the actor (the network used to manipulate the environment). Only the output nodes need to be specified. They should match the actions provided by the agent. More... | |
| int | policyNodeNameCount = 0 |
| The number of elements in the policy node name array More... | |
| float | gamma = 0.99f |
| Reward decay over time More... | |
| GradientDescentTrainingInfo | trainingInfo |
| Gradient descent training parameters More... | |
| int | sequenceLength = 1 |
| LSTM sequence lengths. Can be ignored if there is no LSTM in the graphs. More... | |
 Public Attributes inherited from SmartEngine::ResourceCInfo | |
| const char * | resourceName = nullptr |
| Optional resource name that will be used with Load() and Save() if no other name is provided. More... | |
Detailed Description
Data used to construct an IRLTrainer instance
Member Data Documentation
◆ agentName
| const char* SmartEngine::RLTrainerCInfo::agentName = "" |
Should be a unique name across the data store
◆ context
| IContext* SmartEngine::RLTrainerCInfo::context = nullptr |
The context to perform graph operations within.
◆ dataStore
| IAgentDataStore* SmartEngine::RLTrainerCInfo::dataStore = nullptr |
The data store used to save experience state
◆ gamma
| float SmartEngine::RLTrainerCInfo::gamma = 0.99f |
Reward decay over time
◆ policyNodeNameCount
| int SmartEngine::RLTrainerCInfo::policyNodeNameCount = 0 |
The number of elements in the policy node name array
◆ policyNodeNames
| const char** SmartEngine::RLTrainerCInfo::policyNodeNames = nullptr |
The names of the output nodes of the actor (the network used to manipulate the environment). Only the output nodes need to be specified. They should match the actions provided by the agent.
◆ sequenceLength
| int SmartEngine::RLTrainerCInfo::sequenceLength = 1 |
LSTM sequence lengths. Can be ignored if there is no LSTM in the graphs.
◆ trainingInfo
| GradientDescentTrainingInfo SmartEngine::RLTrainerCInfo::trainingInfo |
Gradient descent training parameters
