Train PG Agent to Balance Cart-Pole System

Open Live Script

This example shows how to train a policy gradient (PG) agent to balance a cart-pole system modeled in MATLAB®. For more information on PG agents, seePolicy Gradient Agents.

For an example that trains a PG agent with a baseline, seeTrain PG Agent with Baseline to Control Double Integrator System.

Cart-Pole MATLAB Environment

The reinforcement learning environment for this example is a pole attached to an unactuated joint on a cart, which moves along a frictionless track. The training goal is to make the pendulum stand upright without falling over.

For this environment:

The upward balanced pendulum position is0radians, and the downward hanging position ispiradians.
The pendulum starts upright with an initial angle between –0.05 and 0.05 radians.
The force action signal from the agent to the environment is from –10 to 10 N.
The observations from the environment are the position and velocity of the cart, the pendulum angle, and the pendulum angle derivative.
The episode terminates if the pole is more than 12 degrees from vertical or if the cart moves more than 2.4 m from the original position.
A reward of +1 is provided for every time step that the pole remains upright. A penalty of –5 is applied when the pendulum falls.

For more information on this model, seeLoad Predefined Control System Environments.

Create Environment Interface

Create a predefined environment interface for the pendulum.

env = rlPredefinedEnv("CartPole-Discrete")

env = CartPoleDiscreteAction with properties: Gravity: 9.8000 MassCart: 1 MassPole: 0.1000 Length: 0.5000 MaxForce: 10 Ts: 0.0200 ThetaThresholdRadians: 0.2094 XThreshold: 2.4000 RewardForNotFalling: 1 PenaltyForFalling: -5 State: [4×1 double]

The interface has a discrete action space where the agent can apply one of two possible force values to the cart, –10 or 10 N.

Obtain the observation and action information from the environment interface.

obsInfo = getObservationInfo(env); numObservations = obsInfo.Dimension(1); actInfo = getActionInfo(env);

Fix the random generator seed for reproducibility.

rng(0)

Create PG Agent

A PG agent decides which action to take given observations using an actor representation. To create the actor, first create a deep neural network with one input (the observation) and one output (the action). The actor network has two outputs, which corresponds to the number of possible actions. For more information on creating a deep neural network policy representation, seeCreate Policies and Value Functions.

actorNetwork = [ featureInputLayer(numObservations,'Normalization','none','Name','state') fullyConnectedLayer(2,'Name','fc') softmaxLayer('Name','actionProb') ];

Specify options for the actor representation usingrlRepresentationOptions.

actorOpts = rlRepresentationOptions(“LearnRate”,1e-2,'GradientThreshold',1);

Create the actor representation using the specified deep neural network and options. You must also specify the action and observation information for the critic, which you obtained from the environment interface. For more information, seerlStochasticActorRepresentation.

actor = rlStochasticActorRepresentation(actorNetwork,obsInfo,actInfo,'Observation',{'state'},actorOpts);

Create the agent using the specified actor representation and the default agent options. For more information, seerlPGAgent.

agent = rlPGAgent(actor);

Train Agent

To train the agent, first specify the training options. For this example, use the following options.

Run each training episode for at most 1000 episodes, with each episode lasting at most 200 time steps.
Display the training progress in the Episode Manager dialog box (set thePlotsoption) and disable the command line display (set theVerboseoption tofalse).
Stop training when the agent receives an average cumulative reward greater than 195 over 100 consecutive episodes. At this point, the agent can balance the pendulum in the upright position.

For more information, seerlTrainingOptions.

trainOpts = rlTrainingOptions(...'MaxEpisodes', 1000,...'MaxStepsPerEpisode', 200,...'Verbose', false,...“阴谋”,'training-progress',...'StopTrainingCriteria','AverageReward',...'StopTrainingValue',195,...'ScoreAveragingWindowLength',100);

You can visualize the cart-pole system by using theplotfunction during training or simulation.

plot(env)

Train the agent using thetrain函数。这个代理是一个计算训练intensive process that takes several minutes to complete. To save time while running this example, load a pretrained agent by settingdoTrainingtofalse. To train the agent yourself, setdoTrainingtotrue.

doTraining = false;ifdoTraining% Train the agent.trainingStats = train(agent,env,trainOpts);else% Load the pretrained agent for the example.load('MATLABCartpolePG.mat','agent');end

Simulate PG Agent

To validate the performance of the trained agent, simulate it within the cart-pole environment. For more information on agent simulation, seerlSimulationOptionsandsim. The agent can balance the cart-pole system even when the simulation time increases to 500 steps.

simOptions = rlSimulationOptions('MaxSteps',500); experience = sim(env,agent,simOptions);

totalReward = sum(experience.Reward)

totalReward = 500