def defaults(cls): # Preprocessing. subsample = 2 frame_skip = 4 history = 4 delta = False frame_max = 2 noop_max = 30 # Architecture. network = 'network_dqn_2015' replay_capacity = 1e5 # 1e6 start_learning = 5e4 # Exploration. epsilon = dict(from_=1.0, to=0.1, test=0.05, over=1e6, offset=start_learning) # Learning. batch_size = 32 sync_target = 2500 # Optimizer. initial_learning_rate = 2.5e-4 optimizer = tf.train.RMSPropOptimizer rms_decay = 0.95 rms_epsilon = 0.1 return merge_dicts(super().defaults(), locals())
def defaults(cls): # Preprocessing. subsample = 2 frame_skip = 4 history = 4 delta = False frame_max = 2 noop_max = 30 # Architecture. learners = 16 apply_gradient = 5 network = 'network_a3c_lstm' scale_critic_loss = 0.5 regularize = 0.01 # Optimizer. initial_learning_rate = 7e-4 optimizer = tf.train.RMSPropOptimizer rms_decay = 0.99 rms_epsilon = 0.1 return merge_dicts(super().defaults(), locals())
def defaults(cls): frameskip = 3 fps = 30 / frameskip sensitivity = 0.3 viewer = Viewer return merge_dicts(super().defaults(), locals())