Data used to construct an IA2CTrainer instance More...
#include <A2CTrainer.h>
Public Attributes | |
| IGraph * | graph = nullptr |
| The graph we are training. This should contain the policy network and value network. More... | |
| ICuriosityModule * | curiosityModule = nullptr |
| Optional curiosity module for additional exploration rewards More... | |
| const char * | valueNodeName = "" |
| The name of the output of the critic node. This node should be a linear layer with one output neuron and no activation function. More... | |
| float | valueCoefficient = 1.0f |
| How much weight the value contributes to the loss More... | |
| float | entropyCoefficient = 0.01f |
| How much weight the entropy contributes to the loss. Entropy is a measure of how random our output is. At the beginning of training, we want random output, but towards the end we want less random output so that we choose paths we know work. More... | |
| int | lookAheadSteps = 2 |
| How many actual experiences we should look at before using an estimate for total rewards this episode. More... | |
| int | minBatchSize = 32 |
| How many data samples we should try to train at a time. More... | |
 Public Attributes inherited from SmartEngine::RLTrainerCInfo | |
| 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 IA2CTrainer instance
Member Data Documentation
◆ curiosityModule
| ICuriosityModule* SmartEngine::A2CTrainerCInfo::curiosityModule = nullptr |
Optional curiosity module for additional exploration rewards
◆ entropyCoefficient
| float SmartEngine::A2CTrainerCInfo::entropyCoefficient = 0.01f |
How much weight the entropy contributes to the loss. Entropy is a measure of how random our output is. At the beginning of training, we want random output, but towards the end we want less random output so that we choose paths we know work.
◆ graph
| IGraph* SmartEngine::A2CTrainerCInfo::graph = nullptr |
The graph we are training. This should contain the policy network and value network.
◆ lookAheadSteps
| int SmartEngine::A2CTrainerCInfo::lookAheadSteps = 2 |
How many actual experiences we should look at before using an estimate for total rewards this episode.
◆ minBatchSize
| int SmartEngine::A2CTrainerCInfo::minBatchSize = 32 |
How many data samples we should try to train at a time.
◆ valueCoefficient
| float SmartEngine::A2CTrainerCInfo::valueCoefficient = 1.0f |
How much weight the value contributes to the loss
◆ valueNodeName
| const char* SmartEngine::A2CTrainerCInfo::valueNodeName = "" |
The name of the output of the critic node. This node should be a linear layer with one output neuron and no activation function.
