tensorforce.core.explorations package

Submodules

tensorforce.core.explorations.constant module

class tensorforce.core.explorations.constant.Constant(constant=0.0, scope='constant', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Explore via adding a constant term.

tf_explore(episode, timestep, action_shape)

tensorforce.core.explorations.epsilon_anneal module

class tensorforce.core.explorations.epsilon_anneal.EpsilonAnneal(initial_epsilon=1.0, final_epsilon=0.1, timesteps=10000, start_timestep=0, scope='epsilon_anneal', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Annealing epsilon parameter based on ratio of current timestep to total timesteps.

tf_explore(episode, timestep, action_shape)

tensorforce.core.explorations.epsilon_decay module

class tensorforce.core.explorations.epsilon_decay.EpsilonDecay(initial_epsilon=1.0, final_epsilon=0.1, timesteps=10000, start_timestep=0, half_lives=10, scope='epsilon_anneal', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Exponentially decaying epsilon parameter based on ratio of difference between current and final epsilon to total timesteps.

tf_explore(episode=0, timestep=0, action_shape=(1, ))

tensorforce.core.explorations.exploration module

class tensorforce.core.explorations.exploration.Exploration(scope='exploration', summary_labels=None)

Bases: object

Abstract exploration object.

static from_spec(spec)

Creates an exploration object from a specification dict.

get_variables()

Returns exploration variables.

Returns:List of variables.

tf_explore(episode, timestep, action_shape)

Creates exploration value, e.g. compute an epsilon for epsilon-greedy or sample normal noise.

tensorforce.core.explorations.linear_decay module

class tensorforce.core.explorations.linear_decay.LinearDecay(scope='exploration', summary_labels=None)

Bases: tensorforce.core.explorations.exploration.Exploration

Linear decay based on episode number.

tf_explore(episode, timestep, action_shape)

tensorforce.core.explorations.ornstein_uhlenbeck_process module

class tensorforce.core.explorations.ornstein_uhlenbeck_process.OrnsteinUhlenbeckProcess(sigma=0.3, mu=0.0, theta=0.15, scope='ornstein_uhlenbeck', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Explores via an Ornstein-Uhlenbeck process.

tf_explore(episode, timestep, action_shape)

Module contents

class tensorforce.core.explorations.Exploration(scope='exploration', summary_labels=None)

Bases: object

Abstract exploration object.

static from_spec(spec)

Creates an exploration object from a specification dict.

get_variables()

Returns exploration variables.

Returns:List of variables.

tf_explore(episode, timestep, action_shape)

Creates exploration value, e.g. compute an epsilon for epsilon-greedy or sample normal noise.

class tensorforce.core.explorations.Constant(constant=0.0, scope='constant', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Explore via adding a constant term.

tf_explore(episode, timestep, action_shape)

class tensorforce.core.explorations.LinearDecay(scope='exploration', summary_labels=None)

Bases: tensorforce.core.explorations.exploration.Exploration

Linear decay based on episode number.

tf_explore(episode, timestep, action_shape)

class tensorforce.core.explorations.EpsilonDecay(initial_epsilon=1.0, final_epsilon=0.1, timesteps=10000, start_timestep=0, half_lives=10, scope='epsilon_anneal', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Exponentially decaying epsilon parameter based on ratio of difference between current and final epsilon to total timesteps.

tf_explore(episode=0, timestep=0, action_shape=(1, ))

class tensorforce.core.explorations.OrnsteinUhlenbeckProcess(sigma=0.3, mu=0.0, theta=0.15, scope='ornstein_uhlenbeck', summary_labels=())

Bases: tensorforce.core.explorations.exploration.Exploration

Explores via an Ornstein-Uhlenbeck process.

tf_explore(episode, timestep, action_shape)