LearnerGroup API#
Configuring a LearnerGroup and Learner actors#
Sets LearnerGroup and Learner worker related configurations. |
Constructing a LearnerGroup#
Builds and returns a new LearnerGroup object based on settings in |
Coordinator of n (possibly remote) Learner workers. |
Learner API#
Constructing a Learner#
Builds and returns a new Learner object based on settings in |
Base class for Learners. |
|
Builds the Learner. |
|
Construct the multi-agent RL module for the learner. |
Implementing a custom RLModule to fit a Learner#
Returns the required APIs for an RLModule to be compatible with this Learner. |
|
Check whether the given |
Performing updates#
Run |
|
Called before gradient-based updates are completed. |
|
Called after gradient-based updates are completed. |
Computing losses#
Computes the loss(es) for the module being optimized. |
|
Computes the loss for a single module. |
Configuring optimizers#
Configures an optimizer for the given module_id. |
|
Configures, creates, and registers the optimizers for this Learner. |
|
Registers an optimizer with a ModuleID, name, param list and lr-scheduler. |
|
Returns a list of (optimizer_name, optimizer instance)-tuples for module_id. |
|
Returns the optimizer object, configured under the given module_id and name. |
|
Returns the list of parameters of a module. |
|
Returns a hashable reference to a trainable parameter. |
|
Reduces the given ParamDict to contain only parameters for given optimizer. |
|
Checks that the given optimizer and parameters are valid for the framework. |
|
Updates the learning rate of the given local optimizer. |
Gradient computation#
Computes the gradients based on the given losses. |
|
Applies potential postprocessing operations on the gradients. |
|
Applies postprocessing operations on the gradients of the given module. |
|
Applies the gradients to the MultiRLModule parameters. |
|
Returns the gradient clipping function to use. |
Saving and restoring#
Saves the state of the implementing class (or |
|
Restores the state of the implementing class from the given path. |
|
Creates a new Checkpointable instance from the given location and returns it. |
|
Returns the implementing class's current state as a dict. |
|
Sets the implementing class' state to the given state dict. |
Adding and removing modules#
Adds a module to the underlying MultiRLModule. |
|
Removes a module from the Learner. |