rlang.agents package

rlang.agents.RLangPolicyAgentClass module

class rlang.agents.RLangPolicyAgentClass.RLangPolicyAgent[source]

Bases: Module

Implementation for an agent that uses an RLang policy

__init__(rlang_policy, epsilon=1e-08, n_actions=2, obs_normalizer=None)[source]
Parameters

  • rlang_policy (Policy) – an RLang policy.

  • epsilon (float) – Exploration term.

  • n_actions (int) – Number of actions.

  • obs_normalizer –

forward(state)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

rlang.agents.RLangQLearningAgentClass module

class rlang.agents.RLangQLearningAgentClass.RLangQLearningAgent[source]

Bases: QLearningAgent

Implementation for a Q Learning agent that utilizes RLang hints

__init__(actions, states, knowledge, name='RLang-Q-learning', use_transition=False, alpha=0.1, gamma=0.99, epsilon=0.1, explore='uniform', anneal=False, default_q=0)[source]
Parameters

  • actions (list) – Contains strings denoting the actions.

  • states (list) – A list of all possible states.

  • knowledge (list) – An RLangKnowledge object.

  • name (str) – Denotes the name of the agent.

  • alpha (float) – Learning rate.

  • gamma (float) – Discount factor.

  • epsilon (float) – Exploration term.

  • explore (str) – One of {softmax, uniform}. Denotes explore policy.

  • default_q (float) – the default value to initialize every entry in the q-table with [by default, set to 0.0]