Actions exploration about tforce_btc_trader HOT 4 OPEN

hypers['agent'] = {
    # 'states_preprocessing': None,
    # 'actions_exploration': None,
    
    'actions_exploration.type':'ornstein_uhlenbeck',
    'actions_exploration.sigma': {
        'type': 'bounded',
        'vals': [0., 1.],
        'guess': .2,
        'hydrate': min_threshold(.05, None)
    },
    'actions_exploration.mu':{
        'type': 'bounded',
        'vals': [0., 1.],
        'guess': .2,
        'hydrate': min_threshold(.05, None)
    },
    'actions_exploration.theta':{
        'type': 'bounded',
        'vals': [0., 1.],
        'guess': .2,
        'hydrate': min_threshold(.05, None)
    },
    # 'reward_preprocessing': None,

    # I'm pretty sure we don't want to experiment any less than .99 for non-terminal reward-types (which are 1.0).
    # .99^500 ~= .6%, so looses value sooner than makes sense for our trading horizon. A trade now could effect
    # something 2-5k steps later. So .999 is more like it (5k steps ~= .6%)
    'discount': 1.,  # {
    #     'type': 'bounded',
    #     'vals': [.9, .99],
    #     'guess': .97
    # },
}

    'actions_exploration': {
        'type': 'ornstein_uhlenbeck',
        'sigma': hp.quniform('exploration.sigma', 0, 1, 0.05),
        'mu': hp.quniform('exploration.mu', 0, 1, 0.05),
        'theta':hp.quniform('exploration.theta', 0, 1, 0.05)
        },