Set approximation model in function approximator object
Modify Deep Neural Networks in Reinforcement Learning Agent
Create an environment with a continuous action space and obtain its observation and action specifications. For this example, load the environment used in the example Compare DDPG Agent to LQR Controller.
Load the predefined environment.
env = rlPredefinedEnv("DoubleIntegrator-Continuous");
Obtain observation and action specifications.
obsInfo = getObservationInfo(env); actInfo = getActionInfo(env);
Create a PPO agent from the environment observation and action specifications. This agent uses default deep neural networks for its actor and critic.
agent = rlPPOAgent(obsInfo,actInfo);
To modify the deep neural networks within a reinforcement learning agent, you must first extract the actor and critic function approximators.
actor = getActor(agent); critic = getCritic(agent);
Extract the deep neural networks from both the actor and critic function approximators.
actorNet = getModel(actor); criticNet = getModel(critic);
The networks are
dlnetwork objects. To view them using the
plot function, you must convert them to
For example, view the actor network.
To validate a network, use
analyzeNetwork. For example, validate the critic network.
You can modify the actor and critic networks and save them back to the agent. To modify the networks, you can use the Deep Network Designer app. To open the app for each network, use the following commands.
In Deep Network Designer, modify the networks. For example, you can add additional layers to your network. When you modify the networks, do not change the input and output layers of the networks returned by
getModel. For more information on building networks, see Build Networks with Deep Network Designer.
To validate the modified network in Deep Network Designer, you must click on Analyze, under the Analysis section. To export the modified network structures to the MATLAB® workspace, generate code for creating the new networks and run this code from the command line. Do not use the exporting option in Deep Network Designer. For an example that shows how to generate and run code, see Create DQN Agent Using Deep Network Designer and Train Using Image Observations.
For this example, the code for creating the modified actor and critic networks is in the
createModifiedNetworks helper script.
Each of the modified networks includes an additional
reluLayer in their main common path. View the modified actor network.
After exporting the networks, insert the networks into the actor and critic function approximators.
actor = setModel(actor,modifiedActorNet); critic = setModel(critic,modifiedCriticNet);
Finally, insert the modified actor and critic function approximators into the actor and critic objects.
agent = setActor(agent,actor); agent = setCritic(agent,critic);
oldFcnAppx — Original function approximator
function approximator object
Original function approximator, specified as one of the following:
rlValueFunctionobject — Value function critic
rlQValueFunctionobject — Q-value function critic
rlVectorQValueFunctionobject — Multi-output Q-value function critic with a discrete action space
rlContinuousDeterministicActorobject — Deterministic policy actor with a continuous action space
rlDiscreteCategoricalActor— Stochastic policy actor with a discrete action space
rlContinuousGaussianActorobject — Stochastic policy actor with a continuous action space
rlContinuousDeterministicTransitionFunctionobject — Continuous deterministic transition function for a model based agent
rlContinuousGaussianTransitionFunctionobject — Continuous Gaussian transition function for a model based agent
rlContinuousDeterministicRewardFunctionobject — Continuous deterministic reward function for a model based agent
rlContinuousGaussianRewardFunctionobject — Continuous Gaussian reward function for a model based agent.
rlIsDoneFunctionobject — Is-done function for a model based agent.
To create an actor or critic function object, use one of the following methods.
model — Function approximation model
Layer objects |
layerGraph object |
DAGNetwork object |
dlnetwork object |
rlTable object | 1-by-2 cell array
Function approximation model, specified as one of the following:
Deep neural network defined as an array of
DAGNetworkobject, or a
dlnetworkobject. The input and output layers of
modelmust have the same names and dimensions as the network returned by
getModelfor the same function object. Here, the output layer is the layer immediately before the output loss layer.
rlTableobject with the same dimensions as the table model defined in
1-by-2 cell array that contains the function handle for a custom basis function and the basis function parameters.
When specifying a new model, you must use the same type of model as the one already
For agents with more than one critic, such as TD3 and SAC agents, you must call
setModel for each critic representation individually, rather
setModel for the array of returned by
critics = getCritic(myTD3Agent); % Modify critic networks. critics(1) = setModel(critics(1),criticNet1); critics(2) = setModel(critics(2),criticNet2); myTD3Agent = setCritic(myTD3Agent,critics);
Version HistoryIntroduced in R2020b
setModel now uses approximator objects instead of representation objects
Using representation objects to create actors and critics for reinforcement learning
agents is no longer recommended. Therefore,
setModel now uses function
approximator objects instead.