getMaxQValue - Obtain maximum estimated value over all possible actions from a Q-value function

  critic with discrete action space, given environment observations - MATLAB ([original](https://www.mathworks.com/help/reinforcement-learning/ref/rl.function.rlqvaluefunction.getmaxqvalue.html)) ([raw](?raw))

Obtain maximum estimated value over all possible actions from a Q-value function critic with discrete action space, given environment observations

Since R2020a

Syntax

Description

[[maxQ](#mw%5Fc5c08050-60d7-48cb-9808-442a8becdf60),[maxActionIndex](#mw%5Fab3ced21-09d5-46b9-99ef-2a889d9582e5)] = getMaxQValue([qValueFcnObj](#mw%5F697aec70-1f1a-4676-8c51-464b65b28d98),[obs](#mw%5F1ba9962d-a5f8-4c42-9704-86b386545b26)) evaluates the discrete-action-space Q-value function criticqValueFcnObj and returns the maximum estimated value over all possible actions maxQ, with the corresponding action indexmaxActionIndex, given environment observationsobs.

example

[[maxQ](#mw%5Fc5c08050-60d7-48cb-9808-442a8becdf60),[maxActionIndex](#mw%5Fab3ced21-09d5-46b9-99ef-2a889d9582e5),[nextState](#mw%5Fe2bb0839-5c6a-4b86-836a-f97996f72144)] = getMaxQValue(___) also returns the updated state of qValueFcnObj when it contains a recurrent neural network.

___ = getMaxQValue(___,UseForward=[useForward](#mw%5F62e98354-62fb-4351-810b-3a8122d309ad%5Fsep%5Fmw%5F7f8a74e4-f9cb-4418-bfe7-55c39bddd077)) allows you to explicitly call a forward pass when computing gradients.

Examples

collapse all

Obtain Maximum Q-Value Function Estimates

Create an observation and action specification objects (or alternatively use getObservationInfo and getActionInfo to extract the specification objects from an environment. For this example, define the observation space as a continuous three-dimensional space, and the action space as a finite set consisting of three possible values (named -1, 0, and 1).

obsInfo = rlNumericSpec([3 1]); actInfo = rlFiniteSetSpec([-1 0 1]);

Create a default DQN agent and extract its critic.

agent = rlDQNAgent(obsInfo,actInfo); critic = getCritic(agent);

Use getMaxQValue to return the maximum value, among the possible actions, given a random observation. Also return the index corresponding to the action that maximizes the value.

[v,i] = getMaxQValue(critic,{rand(3,1)})

Create a batch set of 64 random independent observations. The third dimension is the batch size, while the fourth is the sequence length for any recurrent neural network used by the critic (in this case not used).

batchobs = rand(3,1,64,1);

Obtain maximum values for all the observations.

bv = getMaxQValue(critic,{batchobs}); size(bv)

Select the maximum value corresponding to the 44th observation.

Input Arguments

collapse all

obs — Environment observations

cell array

Environment observations, specified as a cell array with as many elements as there are observation input channels. Each element of obs contains an array of observations for a single observation input channel.

The dimensions of each element in obs are_MO_-by-_LB_-by-LS, where:

• MO corresponds to the dimensions of the associated observation input channel.
• LB is the batch size. To specify a single observation, set LB = 1. To specify a batch of observations, specify LB > 1. If qValueFcnObj has multiple observation input channels, then_LB_ must be the same for all elements of obs.
• LS specifies the sequence length for a recurrent neural network. If qValueFcnObj does not use a recurrent neural network, then LS = 1. IfqValueFcnObj has multiple observation input channels, then_LS_ must be the same for all elements of obs.

LB and_LS_ must be the same for bothact and obs.

For more information on input and output formats for recurrent neural networks, see the Algorithms section of lstmLayer.

useForward — Option to use parallel training

false (default) | true

Option to use forward pass, specified as a logical value. When you specifyUseForward=true the function calculates its outputs usingforward instead of predict. This allows layers such as batch normalization and dropout to appropriately change their behavior for training.

Example: true

Output Arguments

collapse all

maxQ — Maximum Q-value estimate

array

Maximum Q-value estimate across all possible discrete actions, returned as a 1-by-_LB_-by-LS array, where:

• LB is the batch size.
• LS specifies the sequence length for a recurrent neural network. If qValueFcnObj does not use a recurrent neural network, then LS = 1.

maxActionIndex — Action index

array

Action index corresponding to the maximum Q value, returned as a 1-by-_LB_-by-LS array, where:

• LB is the batch size.
• LS specifies the sequence length for a recurrent neural network. If qValueFcnObj does not use a recurrent neural network, then LS = 1.

nextState — Updated state of the critic

cell array

Updated state of qValueFcnObj, returned as a cell array. IfqValueFcnObj does not use a recurrent neural network, thennextState is an empty cell array.

You can set the state of the critic to state using dot notation. For example:

qValueFcnObj.State=state;

Version History

Introduced in R2020a