Navigation

  • index
  • modules |
  • next |
  • previous |
  • Maja Machine Learning Framework v1.0 documentation »
  • API-documentation »
  • Resources »

Policy Search Methods¶

Interface for MMLF policy search methods

MMLF policy search methods must implement the following methods:
  • getActivePolicy
  • getBestPolicy
  • tellFitness
class resources.policy_search.policy_search.PolicySearch¶

Interface for MMLF policy search methods

MMLF optimizers must implement the following methods:
  • getActivePolicy(): Returns the currently active policy

  • getBestPolicy(): Returns the best policy found so far

  • tellFitness(fitnessSample): Gives one fitness sample for the currently

    active policy

static create(policySearchSpec, stateSpace, actionSpace, stateDims)¶

Factory method that creates policy search method based on spec.

getActivePolicy()¶

Returns the currently active policy

getBestPolicy()¶

Returns the best policy found so far

static getPolicySearchDict()¶

Returns dict that contains a mapping from PS name to PS class.

reset()¶

Resets the policy search method

tellFitness(fitnessSample)¶

Gives one fitness sample for the currently active policy

Provides the fitness fitnessSample obtained in one evaluation of the currently active policy.

Fixed Parametrization¶

Policy search method that optimizes the parameters of a fixed policy class

The module contains a policy search method that optimizes the parameters of an externally predefined, parametrized policy class. It can use an arbitrary black-box optimization algorithm for this purpose.

class resources.policy_search.fixed_parametrization.FixedParametrization(policy, optimizer)¶

Policy search method that optimizes the parameters of a policy

The module contains a policy search method that optimizes the parameters of an externally predefined policy.

CONFIG DICT
policy:: A parametrized class of policies
optimizer:: An arbitrary black-box optimizer

Logo

Table Of Contents

  • Tutorials
  • Learn more about...
  • API-documentation
    • MMLF package interface
    • Agents
    • Environments
    • Observables
    • Resources
      • Function Approximators
      • Learning Algorithms
      • Models
      • Optimization
      • Planner
      • Policies
      • Policy Search Methods
      • Skill Discovery
    • Framework

Previous topic

Policies

Next topic

Skill Discovery

This Page

  • Show Source

Quick search

Enter search terms or a module, class or function name.

Navigation

  • index
  • modules |
  • next |
  • previous |
  • Maja Machine Learning Framework v1.0 documentation »
  • API-documentation »
  • Resources »
© Copyright 2011, Jan Hendrik Metzen, Mark Edgington. Created using Sphinx 1.0.7.