example_of_configuration_multiplayers module

An example of a configuration file to launch some the simulations, for the single-player case.

example_of_configuration_multiplayers.HORIZON = 10000

HORIZON : number of time steps of the experiments. Warning Should be >= 10000 to be interesting “asymptotically”.

example_of_configuration_multiplayers.REPETITIONS = 10

REPETITIONS : number of repetitions of the experiments. Warning: Should be >= 10 to be statistically trustworthy.

example_of_configuration_multiplayers.DO_PARALLEL = True

To profile the code, turn down parallel computing

example_of_configuration_multiplayers.N_JOBS = -1

Number of jobs to use for the parallel computations. -1 means all the CPU cores, 1 means no parallelization.

example_of_configuration_multiplayers.NB_PLAYERS = 3

NB_PLAYERS : number of players for the game. Should be >= 2 and <= number of arms.

example_of_configuration_multiplayers.collisionModel(t, arms, players, choices, rewards, pulls, collisions)

The best collision model: none of the colliding users get any reward

example_of_configuration_multiplayers.NB_ARMS = 6

Number of arms for non-hard-coded problems (Bayesian problems)

example_of_configuration_multiplayers.LOWER = 0.0

Default value for the lower value of means

example_of_configuration_multiplayers.AMPLITUDE = 1.0

Default value for the amplitude value of means

example_of_configuration_multiplayers.ARM_TYPE

alias of Arms.Bernoulli.Bernoulli

example_of_configuration_multiplayers.ENVIRONMENT_BAYESIAN = False

True to use bayesian problem

example_of_configuration_multiplayers.MEANS = [0.05, 0.22999999999999998, 0.41, 0.5900000000000001, 0.77, 0.95]

Means of arms for non-hard-coded problems (non Bayesian)

example_of_configuration_multiplayers.configuration = {'averageOn': 0.001, 'collisionModel': <function onlyUniqUserGetsReward>, 'environment': [{'arm_type': <class 'Arms.Bernoulli.Bernoulli'>, 'params': [0.05, 0.22999999999999998, 0.41, 0.5900000000000001, 0.77, 0.95]}], 'finalRanksOnAverage': True, 'horizon': 10000, 'n_jobs': -1, 'players': [Selfish(UCB), Selfish(UCB), Selfish(UCB)], 'plot_lowerbounds': True, 'repetitions': 10, 'successive_players': [[<Policies.SIC_MMAB.SIC_MMAB object>, <Policies.SIC_MMAB.SIC_MMAB object>, <Policies.SIC_MMAB.SIC_MMAB object>], [<Policies.SIC_MMAB.SIC_MMAB_UCB object>, <Policies.SIC_MMAB.SIC_MMAB_UCB object>, <Policies.SIC_MMAB.SIC_MMAB_UCB object>], [<Policies.SIC_MMAB.SIC_MMAB_klUCB object>, <Policies.SIC_MMAB.SIC_MMAB_klUCB object>, <Policies.SIC_MMAB.SIC_MMAB_klUCB object>], [rhoRand(UCB), rhoRand(UCB), rhoRand(UCB)], [rhoRand(kl-UCB), rhoRand(kl-UCB), rhoRand(kl-UCB)], [RandTopM(UCB), RandTopM(UCB), RandTopM(UCB)], [RandTopM(kl-UCB), RandTopM(kl-UCB), RandTopM(kl-UCB)], [MCTopM(UCB), MCTopM(UCB), MCTopM(UCB)], [MCTopM(kl-UCB), MCTopM(kl-UCB), MCTopM(kl-UCB)], [Selfish(UCB), Selfish(UCB), Selfish(UCB)], [Selfish(kl-UCB), Selfish(kl-UCB), Selfish(kl-UCB)], [CentralizedMultiplePlay(UCB), CentralizedMultiplePlay(UCB), CentralizedMultiplePlay(UCB)], [CentralizedMultiplePlay(kl-UCB), CentralizedMultiplePlay(kl-UCB), CentralizedMultiplePlay(kl-UCB)], [<Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>], [<Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>], [<Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>, <Policies.MusicalChair.MusicalChair object>]], 'verbosity': 6}

This dictionary configures the experiments

example_of_configuration_multiplayers.nbArms = 6

Number of arms in the first environment