Get critic representation from reinforcement learning agent
Assume that you have an existing trained reinforcement learning agent. For this example, load the trained agent from Train DDPG Agent to Control Double Integrator System.
Obtain the critic representation from the agent.
critic = getCritic(agent);
Obtain the learnable parameters from the critic.
params = getLearnableParameters(critic);
Modify the parameter values. For this example, simply multiply all of the parameters by
modifiedParams = cellfun(@(x) x*2,params,'UniformOutput',false);
Set the parameter values of the critic to the new modified values.
critic = setLearnableParameters(critic,modifiedParams);
Set the critic in the agent to the new modified critic.
agent = setCritic(agent,critic);
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 Train DDPG Agent to Control Double Integrator System.
Load the predefined environment.
env = rlPredefinedEnv("DoubleIntegrator-Continuous")
env = DoubleIntegratorContinuousAction with properties: Gain: 1 Ts: 0.1000 MaxDistance: 5 GoalThreshold: 0.0100 Q: [2x2 double] R: 0.0100 MaxForce: Inf State: [2x1 double]
Obtain observation and action specifications.
obsInfo = getObservationInfo(env); actInfo = getActionInfo(env);
Create a PPO agent from the environment observation and action specifications.
agent = rlPPOAgent(obsInfo,actInfo);
To modify the deep neural networks within a reinforcement learning agent, you must first extract the actor and critic representations.
actor = getActor(agent); critic = getCritic(agent);
Extract the deep neural networks from both the actor and critic representations.
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 for dlnetwork, 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 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
Each of the modified networks includes an additional
reluLayer in their output path. View the modified actor network.
After exporting the networks, insert the networks into the actor and critic representations.
actor = setModel(actor,modifiedActorNet); critic = setModel(critic,modifiedCriticNet);
Finally, insert the modified actor and critic representations in the actor and critic objects.
agent = setActor(agent,actor); agent = setCritic(agent,critic);
agent— Reinforcement learning agent
Reinforcement learning agent that contains a critic representation, specified as one of the following:
critic— Critic representation
rlQValueRepresentationobject | two-element row vector of
Critic representation object, returned as one of the following:
rlQValueRepresentation object — Returned when
agent is an
rlTD3Agent object with a
Two-element row vector of
rlQValueRepresentation objects —
agent is an
rlSACAgent object with two critics