هل من الممكن تدريب وكيل للتداول في البورصة مع تعزيزات؟ تنفيذ لغة R

# configure critic NN ------------ library('keras') library('R6') learning_rate <- 1e-3 state_names_length <- 12 # just for example a_CustomLayer <- R6::R6Class( "CustomLayer" , inherit = KerasLayer , public = list( call = function(x, mask = NULL) { x - k_mean(x, axis = 2, keepdims = T) } ) ) a_normalize_layer <- function(object) { create_layer(a_CustomLayer, object, list(name = 'a_normalize_layer')) } v_CustomLayer <- R6::R6Class( "CustomLayer" , inherit = KerasLayer , public = list( call = function(x, mask = NULL) { k_concatenate(list(x, x, x), axis = 2) } , compute_output_shape = function(input_shape) { output_shape = input_shape output_shape[[2]] <- input_shape[[2]] * 3L output_shape } ) ) v_normalize_layer <- function(object) { create_layer(v_CustomLayer, object, list(name = 'v_normalize_layer')) } noise_CustomLayer <- R6::R6Class( "CustomLayer" , inherit = KerasLayer , lock_objects = FALSE , public = list( initialize = function(output_dim) { self$output_dim <- output_dim } , build = function(input_shape) { self$input_dim <- input_shape[[2]] sqr_inputs <- self$input_dim ** (1/2) self$sigma_initializer <- initializer_constant(.5 / sqr_inputs) self$mu_initializer <- initializer_random_uniform(minval = (-1 / sqr_inputs), maxval = (1 / sqr_inputs)) self$mu_weight <- self$add_weight( name = 'mu_weight', shape = list(self$input_dim, self$output_dim), initializer = self$mu_initializer, trainable = TRUE ) self$sigma_weight <- self$add_weight( name = 'sigma_weight', shape = list(self$input_dim, self$output_dim), initializer = self$sigma_initializer, trainable = TRUE ) self$mu_bias <- self$add_weight( name = 'mu_bias', shape = list(self$output_dim), initializer = self$mu_initializer, trainable = TRUE ) self$sigma_bias <- self$add_weight( name = 'sigma_bias', shape = list(self$output_dim), initializer = self$sigma_initializer, trainable = TRUE ) } , call = function(x, mask = NULL) { #sample from noise distribution e_i = k_random_normal(shape = list(self$input_dim, self$output_dim)) e_j = k_random_normal(shape = list(self$output_dim)) #We use the factorized Gaussian noise variant from Section 3 of Fortunato et al. eW = k_sign(e_i) * (k_sqrt(k_abs(e_i))) * k_sign(e_j) * (k_sqrt(k_abs(e_j))) eB = k_sign(e_j) * (k_abs(e_j) ** (1/2)) #See section 3 of Fortunato et al. noise_injected_weights = k_dot(x, self$mu_weight + (self$sigma_weight * eW)) noise_injected_bias = self$mu_bias + (self$sigma_bias * eB) output = k_bias_add(noise_injected_weights, noise_injected_bias) output } , compute_output_shape = function(input_shape) { output_shape <- input_shape output_shape[[2]] <- self$output_dim output_shape } ) ) noise_add_layer <- function(object, output_dim) { create_layer( noise_CustomLayer , object , list( name = 'noise_add_layer' , output_dim = as.integer(output_dim) , trainable = T ) ) } critic_input <- layer_input( shape = c(as.integer(state_names_length)) , name = 'critic_input' ) common_layer_dense_1 <- layer_dense( units = 20 , activation = "tanh" ) critic_layer_dense_v_1 <- layer_dense( units = 10 , activation = "tanh" ) critic_layer_dense_v_2 <- layer_dense( units = 5 , activation = "tanh" ) critic_layer_dense_v_3 <- layer_dense( units = 1 , name = 'critic_layer_dense_v_3' ) critic_layer_dense_a_1 <- layer_dense( units = 10 , activation = "tanh" ) # critic_layer_dense_a_2 <- layer_dense( # units = 5 # , activation = "tanh" # ) critic_layer_dense_a_3 <- layer_dense( units = length(acts) , name = 'critic_layer_dense_a_3' ) critic_model_v <- critic_input %>% common_layer_dense_1 %>% critic_layer_dense_v_1 %>% critic_layer_dense_v_2 %>% critic_layer_dense_v_3 %>% v_normalize_layer critic_model_a <- critic_input %>% common_layer_dense_1 %>% critic_layer_dense_a_1 %>% #critic_layer_dense_a_2 %>% noise_add_layer(output_dim = 5) %>% critic_layer_dense_a_3 %>% a_normalize_layer critic_output <- layer_add( list( critic_model_v , critic_model_a ) , name = 'critic_output' ) critic_model_1 <- keras_model( inputs = critic_input , outputs = critic_output ) critic_optimizer = optimizer_adam(lr = learning_rate) keras::compile( critic_model_1 , optimizer = critic_optimizer , loss = 'mse' , metrics = 'mse' ) train.x <- rnorm(state_names_length * 10) train.x <- array(train.x, dim = c(10, state_names_length)) predict(critic_model_1, train.x) layer_name <- 'noise_add_layer' intermediate_layer_model <- keras_model(inputs = critic_model_1$input, outputs = get_layer(critic_model_1, layer_name)$output) predict(intermediate_layer_model, train.x)[1,] critic_model_2 <- critic_model_1