`harmoni_rl.rl_client`

Module Contents

Classes

`RLActionsName`
`PPEnv`
`RLCore`

Attributes

`N_DISCRETE_ACTIONS`
`N_DISCRETE_OBSERVATIONS`
`MIN_REWARD`
`MAX_REWARD`

harmoni_rl.rl_client.N_DISCRETE_ACTIONS = 3

harmoni_rl.rl_client.N_DISCRETE_OBSERVATIONS = 11

harmoni_rl.rl_client.MIN_REWARD

harmoni_rl.rl_client.MAX_REWARD = 20

class harmoni_rl.rl_client.RLActionsName

ACTION1 = '1'

ACTION2 = '2'

ACTION3 = '3'

class harmoni_rl.rl_client.PPEnv(observations, rewards)

Bases: gym.Env

metadata

_next_observation()

step(action)

reset()

render(mode='human', close=False)

class harmoni_rl.rl_client.RLCore

setup(model_dir, model_name, dataset, participant_name, session)

start_training(env, observations, logdir)

test()

batch_rl(observation)