ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

tf_agents.bandits.agents.exp3_mixture_agent.Exp3MixtureAgent

An agent that mixes a set of agents and updates the weights with Exp3.

Inherits From: MixtureAgent, TFAgent

For a reference on EXP3, see Bandit Algorithms by Tor Lattimore and Csaba Szepesvari (https://tor-lattimore.com/downloads/book/book.pdf).

The update uses a slighlty modified version of EXP3 to make sure that the weights do not go to one seemingly good agent in the very beginning. To smooth the weights, two extra measures are taken:

  1. A forgetting factor makes sure that the aggregated reward estimates do not grow indefinitely.
  2. The inverse temperature has a maximum parameter that prevents it from growing indefinitely.

It is generally a good idea to set

forgetting_factor = 1 - (1 / max_inverse_temperature)

so that the two smoothing factors work together nicely.

For every data sample, the agent updates the sub-agent that was used to make the action choice in that sample. For this update to happen, the mixture agent needs to have the information on which sub-agent is "responsible" for the action. This information is in a policy info field mixture_choice_info.

agents List of TF-Agents agents that this mixture agent trains.
variable_collection An instance of Exp3VariableCollection. If not set, A default one will be created. It contains all the variables that are needed to restore the mixture agent, excluding the variables of the subagents.
forgetting A float value in (0, 1]. This is how much the estimated reward aggregates are shrinked in every training step.
max_inverse_temperature This value caps the inverse temperature that would otherwise grow as the square root of the number of samples seen.
name Name fo this instance of Exp3MixtureAgent.

action_spec TensorSpec describing the action produced by the agent.
collect_data_context

collect_data_spec Returns a Trajectory spec, as expected by the collect_policy.
collect_policy Return a policy that can be used to collect data from the environment.
data_context

debug_summaries

policy Return the current policy held by the agent.
summaries_enabled

summarize_grads_and_vars

time_step_spec Describes the TimeStep tensors expected by the agent.
train_sequence_length The number of time steps needed in experience tensors passed to train.

Train requires experience to be a Trajectory containing tensors shaped [B, T, ...]. This argument describes the value of T required.

For example, for non-RNN DQN training, T=2 because DQN requires single transitions.

If this value is None, then train can handle an unknown T (it can be determined at runtime from the data). Most RNN-based agents fall into this category.

train_step_counter

training_data_spec Returns a trajectory spec, as expected by the train() function.

Methods

initialize

View source

Initializes the agent.

Returns
An operation that can be used to initialize the agent.

Raises
RuntimeError If the class was not initialized properly (super.__init__ was not called).

loss

View source

Gets loss from the agent.

If the user calls this from _train, it must be in a tf.GradientTape scope in order to apply gradients to trainable variables. If intermediate gradient steps are needed, _loss and _train will return different values since _loss only supports updating all gradients at once after all losses have been calculated.

Args
experience A batch of experience data in the form of a Trajectory. The structure of experience must match that of self.training_data_spec. All tensors in experience must be shaped [batch, time, ...] where time must be equal to self.train_step_length if that property is not None.
weights (optional). A Tensor, either 0-D or shaped [batch], containing weights to be used when calculating the total train loss. Weights are typically multiplied elementwise against the per-batch loss, but the implementation is up to the Agent.
training Explicit argument to pass to loss. This typically affects network computation paths like dropout and batch normalization.
**kwargs Any additional data as args to loss.

Returns
A LossInfo loss tuple containing loss and info tensors.

Raises
RuntimeError If the class was not initialized properly (super.__init__ was not called).

post_process_policy

View source

Post process policies after training.

The policies of some agents require expensive post processing after training before they can be used. e.g. A Recommender agent might require rebuilding an index of actions. For such agents, this method will return a post processed version of the policy. The post processing may either update the existing policies in place or create a new policy, depnding on the agent. The default implementation for agents that do not want to override this method is to return agent.policy.

Returns
The post processed policy.

preprocess_sequence

View source

Defines preprocess_sequence function to be fed into replay buffers.

This defines how we preprocess the collected data before training. Defaults to pass through for most agents. Structure of experience must match that of self.collect_data_spec.

Args
experience a Trajectory shaped [batch, time, ...] or [time, ...] which represents the collected experience data.

Returns
A post processed Trajectory with the same shape as the input.

train

View source

Trains the agent.

Args
experience A batch of experience data in the form of a Trajectory. The structure of experience must match that of self.training_data_spec. All tensors in experience must be shaped [batch, time, ...] where time must be equal to self.train_step_length if that property is not None.
weights (optional). A Tensor, either 0-D or shaped [batch], containing weights to be used when calculating the total train loss. Weights are typically multiplied elementwise against the per-batch loss, but the implementation is up to the Agent.
**kwargs Any additional data to pass to the subclass.

Returns
A LossInfo loss tuple containing loss and info tensors.

  • In eager mode, the loss values are first calculated, then a train step is performed before they are returned.
  • In graph mode, executing any or all of the loss tensors will first calculate the loss value(s), then perform a train step, and return the pre-train-step LossInfo.

Raises
RuntimeError If the class was not initialized properly (super.__init__ was not called).