setLearnableParameters

Set learnable parameter values of agent, function approximator, or policy object

Syntax

setLearnableParameters(agent)

agent = setLearnableParameters(agent)

newFcn = setLearnableParameters(oldFcn,pars)

newPol = setLearnableParameters(oldPol,pars)

Description

Agent

setLearnableParameters(agent) sets the learnable parameter values specified in pars in the specified agent.

agent = setLearnableParameters(agent) also returns the new agent as an output argument.

Actor or Critic

newFcn = setLearnableParameters(oldFcn,pars) returns a new actor or critic function approximator object, newFcn, with the same structure as the original function object, oldFcn, and the learnable parameter values specified in pars.

Policy

newPol = setLearnableParameters(oldPol,pars) returns a new policy object, newPol, with the same structure as the original function object, oldFcn, and the learnable parameter values specified in pars.

Examples

Modify Critic Parameter Values

Assume that you have an existing trained reinforcement learning agent. For this example, load the trained agent from Compare DDPG Agent to LQR Controller.

load("DoubleIntegDDPG.mat","agent") 

Obtain the critic function approximator from the agent.

critic = getCritic(agent);

Obtain the learnable parameters from the critic.

params = getLearnableParameters(critic)

params=2×1 cell array
    {[-5.0182 -1.5718 -0.3493 -0.1067 -0.0540 -0.0029]}
    {[                                              0]}

Modify the parameter values. For this example, simply multiply all of the parameters by 2.

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.

setCritic(agent,critic);

Display the new parameter values.

getLearnableParameters(getCritic(agent))

ans=2×1 cell array
    {[-10.0364 -3.1436 -0.6987 -0.2135 -0.1080 -0.0059]}
    {[                                               0]}

Modify Actor Parameter Values

Assume that you have an existing trained reinforcement learning agent. For this example, load the trained agent from Compare DDPG Agent to LQR Controller.

load("DoubleIntegDDPG.mat","agent") 

Obtain the actor function approximator from the agent.

actor = getActor(agent);

Obtain the learnable parameters from the actor.

params = getLearnableParameters(actor)

params=2×1 cell array
    {[-15.5717 -7.1444]}
    {[               0]}

Modify the parameter values. For this example, simply multiply all of the parameters by 2.

modifiedParams = cellfun(@(x) x*2,params,"UniformOutput",false);

Set the parameter values of the actor to the new modified values.

actor = setLearnableParameters(actor,modifiedParams);

Set the actor in the agent to the new modified actor.

setActor(agent,actor);

Display the new parameter values.

getLearnableParameters(getActor(agent))

ans=2×1 cell array
    {[-31.1433 -14.2887]}
    {[                0]}

Input Arguments

agent — Reinforcement learning agent

reinforcement learning agent object

Reinforcement learning agent, specified as one of the following objects:

• rlQAgent

• rlSARSAAgent

• rlDQNAgent

• rlPGAgent

• rlDDPGAgent

• rlTD3Agent

• rlACAgent

• rlSACAgent

• rlPPOAgent

• rlTRPOAgent

• Custom agent — For more information, see Create Custom Reinforcement Learning Agents.

Note

agent is an handle object. Therefore its parameters are updated by setLearnableParameters whether agent is returned as an output argument or not. For more information about handle objects, see Handle Object Behavior.

oldFcn — Original actor or critic function object

reinforcement learning function approximator object

Original function approximator object, specified as one of the following:

• rlValueFunction object — Value function critic

• rlQValueFunction object — Q-value function critic

• rlVectorQValueFunction object — Multi-output Q-value function critic with a discrete action space

• rlContinuousDeterministicActor object — Deterministic policy actor with a continuous action space

• rlDiscreteCategoricalActor object — Stochastic policy actor with a discrete action space

• rlContinuousGaussianActor object — Stochastic policy actor with a continuous action space

• rlContinuousDeterministicTransitionFunction object — Continuous deterministic transition function for neural network environments

• rlContinuousGaussianTransitionFunction object — Continuous Gaussian transition function for neural network environments

• rlContinuousDeterministicRewardFunction object — Continuous deterministic reward function for neural network environments

• rlContinuousGaussianRewardFunction object — Continuous Gaussian reward function for neural network environments

• rlIsDoneFunction object — IsDone function for neural network environments

To create an actor or critic function object, use one of the following methods.

• Create a function object directly.

• Obtain the existing critic from an agent using getCritic.

• Obtain the existing actor from an agent using getActor.

oldPol — Reinforcement learning policy

rlMaxQPolicy | rlEpsilonGreedyPolicy | rlDeterministicActorPolicy | rlAdditiveNoisePolicy | rlStochasticActorPolicy

Reinforcement learning policy, specified as one of the following objects:

• rlMaxQPolicy

• rlEpsilonGreedyPolicy

• rlDeterministicActorPolicy

• rlAdditiveNoisePolicy

• rlStochasticActorPolicy

pars — Learnable parameter values

cell array

Learnable parameter values for the representation object, specified as a cell array. The parameters in pars must be compatible with the structure and parameterization of the agent, function approximator, or policy object passed as a first argument.

To obtain a cell array of learnable parameter values from an existing agent, function approximator, or policy object , which you can then modify, use the getLearnableParameters function.

Output Arguments

newFcn — New actor or critic object

rlValueFunction object | rlQValueFunction object | rlVectorQValueFunction object | rlContinuousDeterministicActor object | rlDiscreteCategoricalActor object | rlContinuousGaussianActor object

New actor or critic object, returned as a function object of the same type as oldFcn. Except of its new learnable parameter values, newFcn is the same as oldFcn.

newPol — New reinforcement learning policy

rlMaxQPolicy | rlEpsilonGreedyPolicy | rlDeterministicActorPolicy | rlAdditiveNoisePolicy | rlStochasticActorPolicy

New reinforcement learning policy, returned as a policy object of the same type as oldPol. Apart from the learnable parameter values, newPol is the same as oldPol.

agent — Updated agent

reinforcement learning agent object

Updated agent, returned as an agent object. Note that agent is an handle object. Therefore its parameters are updated by setLearnableParameters whether agent is returned as an output argument or not. For more information about handle objects, see Handle Object Behavior.

Version History

Introduced in R2019a

R2022a: setLearnableParameters 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, setLearnableParameters now uses function approximator objects instead.

R2020a: setLearnableParameterValues is now setLearnableParameters

setLearnableParameterValues is now setLearnableParameters. To update your code, change the function name from setLearnableParameterValues to setLearnableParameters. The syntaxes are equivalent.