# Module: tf_agents.bandits.policies

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/bandits/policies/__init__.py) |

Module importing all policies.

## Modules

[`bernoulli_thompson_sampling_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/bernoulli_thompson_sampling_policy) module: Policy for Bernoulli Thompson Sampling.

[`boltzmann_reward_prediction_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/boltzmann_reward_prediction_policy) module: Policy for reward prediction and boltzmann exploration.

[`categorical_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/categorical_policy) module: Policy that chooses actions based on a categorical distribution.

[`constraints`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/constraints) module: An API for representing constraints.

[`falcon_reward_prediction_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/falcon_reward_prediction_policy) module: Policy that samples actions based on the FALCON algorithm.

[`greedy_multi_objective_neural_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/greedy_multi_objective_neural_policy) module: Policy for greedy multi-objective prediction.

[`greedy_reward_prediction_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/greedy_reward_prediction_policy) module: Policy for greedy reward prediction.

[`lin_ucb_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/lin_ucb_policy) module: Linear UCB Policy.

[`linalg`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/linalg) module: Utility code for linear algebra functions.

[`linear_bandit_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/linear_bandit_policy) module: Linear Bandit Policy.

[`linear_thompson_sampling_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/linear_thompson_sampling_policy) module: Linear Thompson Sampling Policy.

[`loss_utils`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/loss_utils) module: Loss utility code.

[`mixture_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/mixture_policy) module: A policy class that chooses from a set of policies to get the actions from.

[`neural_linucb_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/neural_linucb_policy) module: Neural + LinUCB Policy.

[`ranking_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/ranking_policy) module: Ranking policy.

[`reward_prediction_base_policy`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/bandits/policies/reward_prediction_base_policy) module: Base policy that samples actions based on predicted rewards.