AIToolbox
A library that offers tools for AI problem solving.
EpsilonPolicy.hpp
Go to the documentation of this file.
1 #ifndef AI_TOOLBOX_FACTORED_MDP_EPSILON_POLICY_HEADER_FILE
2 #define AI_TOOLBOX_FACTORED_MDP_EPSILON_POLICY_HEADER_FILE
3 
6 
7 namespace AIToolbox::Factored::MDP {
11  class EpsilonPolicy : public EpsilonPolicyInterface<State, State, Action> {
12  public:
14 
27  EpsilonPolicy(const EpsilonBase::Base & p, double epsilon = 0.1);
28 
29  protected:
35  virtual Action sampleRandomAction() const;
36 
42  virtual double getRandomActionProbability() const;
43 
44  // Used to sampled random actions
45  mutable std::vector<std::uniform_int_distribution<size_t>> randomDistribution_;
46  };
47 }
48 
49 #endif
AIToolbox::Factored::MDP::EpsilonPolicy::sampleRandomAction
virtual Action sampleRandomAction() const
This function returns a random action in the Action space.
AIToolbox::Factored::MDP
Definition: CooperativePrioritizedSweeping.hpp:13
AIToolbox::Factored::MDP::EpsilonPolicy::randomDistribution_
std::vector< std::uniform_int_distribution< size_t > > randomDistribution_
Definition: EpsilonPolicy.hpp:45
AIToolbox::Factored::MDP::EpsilonPolicy::getRandomActionProbability
virtual double getRandomActionProbability() const
This function returns the probability of picking a random action.
AIToolbox::PolicyInterface< State, State, Action >
AIToolbox::Factored::MDP::EpsilonPolicy
This class represents an epsilon-greedy policy for Factored MDPs.
Definition: EpsilonPolicy.hpp:11
AIToolbox::Factored::Action
Factors Action
Definition: Types.hpp:69
AIToolbox::EpsilonPolicyInterface
This class is a policy wrapper for epsilon action choice.
Definition: EpsilonPolicyInterface.hpp:29
AIToolbox::Factored::MDP::EpsilonPolicy::EpsilonPolicy
EpsilonPolicy(const EpsilonBase::Base &p, double epsilon=0.1)
Basic constructor.
Types.hpp
EpsilonPolicyInterface.hpp