Actor-Critic

Classical Actor-Critic Methods

class mushroom_rl.algorithms.actor_critic.classic_actor_critic.COPDAC_Q(mdp_info, policy, mu, alpha_theta, alpha_omega, alpha_v, value_function_features=None, policy_features=None)

Bases: mushroom_rl.algorithms.agent.Agent

Compatible off-policy deterministic actor-critic algorithm. “Deterministic Policy Gradient Algorithms”. Silver D. et al.. 2014.

__init__(mdp_info, policy, mu, alpha_theta, alpha_omega, alpha_v, value_function_features=None, policy_features=None)

Constructor.

Parameters:

• mu (Regressor) – regressor that describe the deterministic policy to be learned i.e., the deterministic mapping between state and action.
• alpha_theta (Parameter) – learning rate for policy update;
• alpha_omega (Parameter) – learning rate for the advantage function;
• alpha_v (Parameter) – learning rate for the value function;
• value_function_features (Features, None) – features used by the value function approximator;
• policy_features (Features, None) – features used by the policy.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC(mdp_info, policy, alpha_theta, alpha_v, lambda_par=0.9, value_function_features=None, policy_features=None)

Bases: mushroom_rl.algorithms.agent.Agent

Stochastic Actor critic in the episodic setting as presented in: “Model-Free Reinforcement Learning with Continuous Action in Practice”. Degris T. et al.. 2012.

__init__(mdp_info, policy, alpha_theta, alpha_v, lambda_par=0.9, value_function_features=None, policy_features=None)

Constructor.

Parameters:

• alpha_theta (Parameter) – learning rate for policy update;
• alpha_v (Parameter) – learning rate for the value function;
• lambda_par (float, 9) – trace decay parameter;
• value_function_features (Features, None) – features used by the value function approximator;
• policy_features (Features, None) – features used by the policy.

episode_start()

Called by the agent when a new episode starts.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.classic_actor_critic.StochasticAC_AVG(mdp_info, policy, alpha_theta, alpha_v, alpha_r, lambda_par=0.9, value_function_features=None, policy_features=None)

Bases: mushroom_rl.algorithms.actor_critic.classic_actor_critic.stochastic_ac.StochasticAC

Stochastic Actor critic in the average reward setting as presented in: “Model-Free Reinforcement Learning with Continuous Action in Practice”. Degris T. et al.. 2012.

__init__(mdp_info, policy, alpha_theta, alpha_v, alpha_r, lambda_par=0.9, value_function_features=None, policy_features=None)

Constructor.

Parameters:alpha_r (Parameter) – learning rate for the reward trace.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

Deep Actor-Critic Methods

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.DeepAC(mdp_info, policy, actor_optimizer, parameters)

Bases: mushroom_rl.algorithms.agent.Agent

Base class for algorithms that uses the reparametrization trick, such as SAC, DDPG and TD3.

__init__(mdp_info, policy, actor_optimizer, parameters)

Constructor.

Parameters:

• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• parameters – policy parameters to be optimized.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_optimize_actor_parameters(loss)

Method used to update actor parameters to maximize a given loss.

Parameters:loss (torch.tensor) – the loss computed by the algorithm.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.A2C(mdp_info, policy, actor_optimizer, critic_params, ent_coeff, max_grad_norm=None, critic_fit_params=None)

Bases: mushroom_rl.algorithms.actor_critic.deep_actor_critic.deep_actor_critic.DeepAC

Advantage Actor Critic algorithm (A2C). Synchronous version of the A3C algorithm. “Asynchronous Methods for Deep Reinforcement Learning”. Mnih V. et. al.. 2016.

__init__(mdp_info, policy, actor_optimizer, critic_params, ent_coeff, max_grad_norm=None, critic_fit_params=None)

Constructor.

Parameters:

• policy (TorchPolicy) – torch policy to be learned by the algorithm;
• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• critic_params (dict) – parameters of the critic approximator to build;
• ent_coeff (float, 0) – coefficient for the entropy penalty;
• max_grad_norm (float, None) – maximum norm for gradient clipping. If None, no clipping will be performed, unless specified otherwise in actor_optimizer;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_optimize_actor_parameters(loss)

Method used to update actor parameters to maximize a given loss.

Parameters:loss (torch.tensor) – the loss computed by the algorithm.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.DDPG(mdp_info, policy_class, policy_params, actor_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, tau, policy_delay=1, critic_fit_params=None)

Bases: mushroom_rl.algorithms.actor_critic.deep_actor_critic.deep_actor_critic.DeepAC

Deep Deterministic Policy Gradient algorithm. “Continuous Control with Deep Reinforcement Learning”. Lillicrap T. P. et al.. 2016.

__init__(mdp_info, policy_class, policy_params, actor_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, tau, policy_delay=1, critic_fit_params=None)

Constructor.

Parameters:

• policy_class (Policy) – class of the policy;
• policy_params (dict) – parameters of the policy to build;
• actor_params (dict) – parameters of the actor approximator to build;
• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• critic_params (dict) – parameters of the critic approximator to build;
• batch_size (int) – the number of samples in a batch;
• initial_replay_size (int) – the number of samples to collect before starting the learning;
• max_replay_size (int) – the maximum number of samples in the replay memory;
• tau (float) – value of coefficient for soft updates;
• policy_delay (int, 1) – the number of updates of the critic after which an actor update is implemented;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator;

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_next_q(next_state, absorbing)

Parameters:

• next_state (np.ndarray) – the states where next action has to be evaluated;
• absorbing (np.ndarray) – the absorbing flag for the states in next_state.

Returns:

Action-values returned by the critic for next_state and the action returned by the actor.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_optimize_actor_parameters(loss)

Method used to update actor parameters to maximize a given loss.

Parameters:loss (torch.tensor) – the loss computed by the algorithm.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.TD3(mdp_info, policy_class, policy_params, actor_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, tau, policy_delay=2, noise_std=0.2, noise_clip=0.5, critic_fit_params=None)

Bases: mushroom_rl.algorithms.actor_critic.deep_actor_critic.ddpg.DDPG

Twin Delayed DDPG algorithm. “Addressing Function Approximation Error in Actor-Critic Methods”. Fujimoto S. et al.. 2018.

__init__(mdp_info, policy_class, policy_params, actor_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, tau, policy_delay=2, noise_std=0.2, noise_clip=0.5, critic_fit_params=None)

Constructor.

Parameters:

• policy_class (Policy) – class of the policy;
• policy_params (dict) – parameters of the policy to build;
• actor_params (dict) – parameters of the actor approximator to build;
• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• critic_params (dict) – parameters of the critic approximator to build;
• batch_size (int) – the number of samples in a batch;
• initial_replay_size (int) – the number of samples to collect before starting the learning;
• max_replay_size (int) – the maximum number of samples in the replay memory;
• tau (float) – value of coefficient for soft updates;
• policy_delay (int, 2) – the number of updates of the critic after which an actor update is implemented;
• noise_std (float, 2) – standard deviation of the noise used for policy smoothing;
• noise_clip (float, 5) – maximum absolute value for policy smoothing noise;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator.

_next_q(next_state, absorbing)

Parameters:

• next_state (np.ndarray) – the states where next action has to be evaluated;
• absorbing (np.ndarray) – the absorbing flag for the states in next_state.

Returns:

Action-values returned by the critic for next_state and the action returned by the actor.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_optimize_actor_parameters(loss)

Method used to update actor parameters to maximize a given loss.

Parameters:loss (torch.tensor) – the loss computed by the algorithm.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.SAC(mdp_info, actor_mu_params, actor_sigma_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, warmup_transitions, tau, lr_alpha, target_entropy=None, critic_fit_params=None)

Bases: mushroom_rl.algorithms.actor_critic.deep_actor_critic.deep_actor_critic.DeepAC

Soft Actor-Critic algorithm. “Soft Actor-Critic Algorithms and Applications”. Haarnoja T. et al.. 2019.

__init__(mdp_info, actor_mu_params, actor_sigma_params, actor_optimizer, critic_params, batch_size, initial_replay_size, max_replay_size, warmup_transitions, tau, lr_alpha, target_entropy=None, critic_fit_params=None)

Constructor.

Parameters:

• actor_mu_params (dict) – parameters of the actor mean approximator to build;
• actor_sigma_params (dict) – parameters of the actor sigm approximator to build;
• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• critic_params (dict) – parameters of the critic approximator to build;
• batch_size (int) – the number of samples in a batch;
• initial_replay_size (int) – the number of samples to collect before starting the learning;
• max_replay_size (int) – the maximum number of samples in the replay memory;
• warmup_transitions (int) – number of samples to accumulate in the replay memory to start the policy fitting;
• tau (float) – value of coefficient for soft updates;
• lr_alpha (float) – Learning rate for the entropy coefficient;
• target_entropy (float, None) – target entropy for the policy, if None a default value is computed ;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_next_q(next_state, absorbing)

Parameters:

• next_state (np.ndarray) – the states where next action has to be evaluated;
• absorbing (np.ndarray) – the absorbing flag for the states in next_state.

Returns:

Action-values returned by the critic for next_state and the action returned by the actor.

_optimize_actor_parameters(loss)

Method used to update actor parameters to maximize a given loss.

Parameters:loss (torch.tensor) – the loss computed by the algorithm.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.TRPO(mdp_info, policy, critic_params, ent_coeff=0.0, max_kl=0.001, lam=1.0, n_epochs_line_search=10, n_epochs_cg=10, cg_damping=0.01, cg_residual_tol=1e-10, quiet=True, critic_fit_params=None)

Bases: mushroom_rl.algorithms.agent.Agent

Trust Region Policy optimization algorithm. “Trust Region Policy Optimization”. Schulman J. et al.. 2015.

__init__(mdp_info, policy, critic_params, ent_coeff=0.0, max_kl=0.001, lam=1.0, n_epochs_line_search=10, n_epochs_cg=10, cg_damping=0.01, cg_residual_tol=1e-10, quiet=True, critic_fit_params=None)

Constructor.

Parameters:

• policy (TorchPolicy) – torch policy to be learned by the algorithm
• critic_params (dict) – parameters of the critic approximator to build;
• ent_coeff (float, 0) – coefficient for the entropy penalty;
• max_kl (float, 001) – maximum kl allowed for every policy update;
• float (lam) – lambda coefficient used by generalized advantage estimation;
• n_epochs_line_search (int, 10) – maximum number of iterations of the line search algorithm;
• n_epochs_cg (int, 10) – maximum number of iterations of the conjugate gradient algorithm;
• cg_damping (float, 1e-2) – damping factor for the conjugate gradient algorithm;
• cg_residual_tol (float, 1e-10) – conjugate gradient residual tolerance;
• quiet (bool, True) – if true, the algorithm will print debug information;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.

class mushroom_rl.algorithms.actor_critic.deep_actor_critic.PPO(mdp_info, policy, actor_optimizer, critic_params, n_epochs_policy, batch_size, eps_ppo, lam, quiet=True, critic_fit_params=None)

Bases: mushroom_rl.algorithms.agent.Agent

Proximal Policy Optimization algorithm. “Proximal Policy Optimization Algorithms”. Schulman J. et al.. 2017.

__init__(mdp_info, policy, actor_optimizer, critic_params, n_epochs_policy, batch_size, eps_ppo, lam, quiet=True, critic_fit_params=None)

Constructor.

Parameters:

• policy (TorchPolicy) – torch policy to be learned by the algorithm
• actor_optimizer (dict) – parameters to specify the actor optimizer algorithm;
• critic_params (dict) – parameters of the critic approximator to build;
• n_epochs_policy (int) – number of policy updates for every dataset;
• batch_size (int) – size of minibatches for every optimization step
• eps_ppo (float) – value for probability ratio clipping;
• float (lam) – lambda coefficient used by generalized advantage estimation;
• quiet (bool, True) – if true, the algorithm will print debug information;
• critic_fit_params (dict, None) – parameters of the fitting algorithm of the critic approximator.

fit(dataset)

Fit step.

Parameters:dataset (list) – the dataset.

_add_save_attr(**attr_dict)

Add attributes that should be saved for an agent.

Parameters:attr_dict (dict) – dictionary of attributes mapped to the method that should be used to save and load them.

_post_load()

This method can be overwritten to implement logic that is executed after the loading of the agent.

copy()

Returns:A deepcopy of the agent.

draw_action(state)

Return the action to execute in the given state. It is the action returned by the policy or the action set by the algorithm (e.g. in the case of SARSA).

Parameters:state (np.ndarray) – the state where the agent is. Returns:The action to be executed.

episode_start()

Called by the agent when a new episode starts.

classmethod load(path)

Load and deserialize the agent from the given location on disk.

Parameters:path (string) – Relative or absolute path to the agents save location. Returns:The loaded agent.

save(path)

Serialize and save the agent to the given path on disk.

Parameters:path (string) – Relative or absolute path to the agents save location.

stop()

Method used to stop an agent. Useful when dealing with real world environments, simulators, or to cleanup environments internals after a core learn/evaluate to enforce consistency.