Metadata-Version: 2.4
Name: statisticalRL-learners
Version: 2.2507
Summary: Learners for the Statistical Reinforcement Learning project
Author-email: Odalric-Ambym Maillard <odalric.maillard@inria.fr>
License: MIT
Project-URL: Homepage, https://github.com/StatisticalRL/learners
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: six==1.16.0
Requires-Dist: gymnasium==1.2.0
Requires-Dist: numpy==1.24.3
Requires-Dist: networkx==2.8.8
Requires-Dist: matplotlib==3.7.2
Requires-Dist: scipy==1.15.2
Requires-Dist: pydot==1.4.2
Dynamic: license-file

# Learners
Learning Agents for Statistical Reinforcement Learning


## Installation

    pip install statisticalRL-learners


## Test
You need to install statisticalRL-environments and statisticalRL-experiments before testing.

    pip install statisticalRL-environments
    pip install statisticalRL-experiments


# List of learners:
    
    
    Random
    Human
    Uniform

    MABs:
        MABOracle
        FTL
        UCB
        TS
        IMED
        BESA
    MDPs_dicrete:
        MDPOracle
        QLearning
        AdaQLearning
        IMED-RL
        KL-UCRL
        MED-RL
        PSRL
        UCRL2
        UCRL2.2
        UCRL2B
        UCRL2B-detR
        UCRL3
        UCRL3-lazy
        Known dynamics:
            IMED-KD
            PSRL-KD
            TS-KD
            UCB-KD
            UCRL3-KD
            UCRL3-KD-lazy
        Equivalence structure:
            CUCRL
            CUCRL-detR
            UCRL_SA_oracle
            UCRL_SA


# Usage

You can run an instance of a learner on an environment from StatisticalRL library.
