Large Reward Research Articles

The Role of Dopamine in Impulsivity and Substance Abuse: A Narrative Review

Substance use disorder (SUD), based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), is defined by symptoms caused by utilizing a substance that a person continues taking despite its negative effects. Impulsive decision making is commonly defined as a reduced ability to choose a delayed large reward instead of a small immediate reward. Dopamine has been implicated as a prominent neurotransmitter implicated in the development and pattern of addiction and impulsivity, especially in regard to substance use disorder. Discovery as a key player in the development of addiction dates to the 1950s, with a study performed by Olds and Milner on rats placed in a Skinner box. Their original discovery is part of the beginning of what would become the search into the main mechanistic source of addiction, and how exactly it works at a cellular, physiological, and psychological level. The dopaminergic pathways of our brains are well-studied. It is well established that most of the dopaminergic neurons of the brain are located in the ventral mid-brain and consists of four main pathways: mesocortical, mesolimbic, nigrostriatal, and tuberoinfundibular pathways. Dopamine acts various receptors, with dopamine (D) receptors 1, 2, and 3 playing a major role in motor function and receptors D1 and D2 playing a major role in reward. There are additional studies warranted, especially finding ways to manipulate the dopaminergic system to treat addiction disorders of all varieties. The focus of the present investigation is to delve into the current literature regarding dopamine and its clinical implications in substance use disorder and impulsive behavior.

Neural and Behavioral Correlates of Binge Eating in 9- to 10-Year-Old Children

This observational study compared children with and without binge eating (BE) on biobehavioral measures of reward responsiveness, inhibitory control, and emotion processes, while accounting for the impact of weight. Children aged 9 to 10 years completed the baseline wave of the Adolescent Brain Cognitive Development Study (316 with BE; 7,681 without BE [no-BE]). The prevalence of binge-eating disorder in the BE group was 17.0%; clinically significant internalizing and externalizing symptoms were endorsed by 8.5% and 4.5% of the sample, respectively. The monetary incentive delay (MID) task, stop signal task (SST), and emotional N-Back (EN-Back) task were administered during neuroimaging. Analyses assessed effects of group (BE vs no-BE) on task performance and corresponding neural signal in regions of interest (ROIs). Weight status was evaluated as a covariate and as a moderator of effects. Adjusting for weight status, the BE group (vs no-BE) group showed lower activation during anticipation of reward, specifically large reward (vs no reward), in the composite ROI consisting of the dorsal striatum, nucleus accumbens, orbital frontal gyrus, amygdala, and insula. Groups did not differ significantly in other behavioral or neural outcomes. No interactions between group and weight status were observed. Blunted anticipatory responses to monetary reward were associated with binge eating during peri-adolescence and may play a role in binge eating pathophysiology. Results challenge prior findings in BE that may be confounded by weight, and highlight the importance of future prospective research across binge-eating disorder stage of illness.

Genome-wide association study of delay discounting in Heterogeneous Stock rats.

Delay discounting refers to the behavioral tendency to devalue rewards as a function of their delay in receipt. Heightened delay discounting has been associated with substance use disorders and multiple co-occurring psychopathologies. Human and animal genetic studies have established that delay discounting is heritable, but only a few associated genes have been identified. We aimed to identify novel genetic loci associated with delay discounting through a genome-wide association study (GWAS) using Heterogeneous Stock (HS) rats, a genetically diverse outbred population derived from eight inbred founder strains. We assessed delay discounting in 650 male and female HS rats using an adjusting amount procedure in which rats chose between smaller immediate sucrose rewards or a larger reward at various delays. Preference switch points were calculated and both exponential and hyperbolic functions were fitted to these indifference points. Area under the curve (AUC) and the discounting parameter k of both functions were used as delay discounting measures. GWAS for AUC, exponential k, and one indifference point identified significant loci on chromosomes 20 and 14. The gene Slc35f1, which encodes a member of the solute carrier family, was the sole gene within the chromosome 20 locus. That locus also contained an eQTL for Slc35f1, suggesting that heritable differences in the expression might be responsible for the association with behavior. Adgrl3, which encodes a latrophilin subfamily G-protein coupled receptor, was the sole gene within the chromosome 14 locus. These findings implicate novel genes in delay discounting and highlight the need for further exploration.

Pre-movement muscle co-contraction associated with motor performance deterioration under high reward conditions

Reward usually enhances task performance, but exceptionally large rewards can impede performance due to psychological pressure. In this study, we investigated motor activity changes in high-reward situations and identified indicators for performance decline. Fourteen healthy adults practiced a velocity-dependent right-hand motor task for three days, followed by a test day with varying monetary reward for each trial. Participants were divided into low performers (LPs) and high performers (HPs) according to whether success rate decreased or increased, respectively, on the highest reward trials compared to lower reward trials. Both LPs and HPs demonstrated increased hand velocity during higher reward trials, but only LPs exhibited a significant increase in velocity variance. There was also a negative correlation between the pre-movement co-contraction index (CCI) of the biceps and triceps muscles and success rate on the highest reward trials. This correlation was confirmed in a second experiment with 12 newly recruited participants, suggesting that pre-movement CCI is a marker for performance decline caused by high reward. These findings suggest that interventions to reduce pre-movement CCI such as biofeedback training could be useful for preventing the paradoxical decline in motor performance associated with high rewards.

The perceived controllability of negatively-valenced episodic future thinking modulates delay discounting

ABSTRACT Intertemporal decision-making is important for both economy and physical health. Nevertheless, in daily life, individuals tend to prefer immediate and smaller rewards to delayed and larger rewards, which is known as delay discounting (DD). Episodic future thinking (EFT) has been proven to influence DD. However, there is still no inconsistent conclusion on the effect of negative EFT on DD. Considering the perceived controllability of negative EFT may address the issue (Controllability refers to the extent to which progress and result of an event could be controlled by ourselves). In the current study, we manipulated EFT conditions (baseline, neutral EFT, negative-controllable EFT and negative-uncontrollable EFT), delayed time (i.e. 1 week, 1 month, 3 months, 6 months, 1 year and 3 years) and reward magnitude (small, large). We mainly found that when experiencing negative-uncontrollable EFT compared to negative-controllable EFT in the delayed time of 6 months with large rewards, individuals chose more delayed rewards, suggesting that negative-uncontrollable EFT effectively reduced DD under conditions of both large-magnitude reward and longer delayed time. The current study provides new insight for healthy groups on optimising EFT. In that case, individuals are able to gain long-term benefits in financial management and healthcare.

Political and cultural situation in Kazakhstan in the XVIII–XIX centuries (historical aspect)

The article describes the political situation and cultural situation of the Kazakh land in the period of the Russian Empire and describes the fact that in the XVIII–XIX centuries, the Tsarist authorities carried out various reforms for the final rule of the Kazakh steppe, expanding the countryethnic basis of the Kazakh people, dividing the ethnic groups, dividing them into provinces and districts, depriving the country of integrity. Our article reflects the colonial policy of the Tsarist government towards the Kazakh Steppe, which in some cases was tactically different from the open robbery attacks of the Khiva and Kokand khanates. It is indicated that the Tsarist government began to use an underground policy that led to the exposure of the Kazakh people to the influence of the Russian state and constant subordination to that state. The article also analyzes the policy of the Tsarist government, how the rulers of the Kazakh steppes work for them, buy them with a large reward.

Frustrative nonreward: Detailed c-Fos expression patterns in the amygdala after consummatory successive negative contrast

The amygdala has been implicated in frustrative nonreward induced by unexpected reward downshifts, using paradigms like consummatory successive negative contrast (cSNC). However, existing evidence comes from experiments involving the central and basolateral nuclei on a broad level. Moreover, whether the amygdala’s involvement in reward downshift requires a cSNC effect (i.e., greater suppression in downshifted animals than in unshifted controls) or just consummatory suppression without a cSNC effect, remains unclear. Three groups were exposed to (1) a large reward disparity leading to a cSNC effect (32-to-2% sucrose), (2) a small reward disparity involving consummatory suppression in the absence of a cSNC effect (8-to-2% sucrose), and (3) an unshifted control (2% sucrose). Brains obtained after the first reward downshift session were processed for c-Fos expression, a protein often used as a marker for neural activation. c-Fos-positive cells were counted in the anterior, medial, and posterior portions (A/P axis) of ten regions of the rat basolateral, central, and medial amygdala. c-Fos expression was higher in 32-to-2% sucrose downshift animals than in the other two groups in four regions: the anterior and the medial lateral basal amygdala, the medial capsular central amygdala, and the anterior anterio-ventral medial amygdala. None of the areas exhibited differential c-Fos expression between the 8-to-2% sucrose downshift and the unshifted conditions. Thus, amygdala activation requires exposure to a substantial reward disparity. This approach has identified, for the first time, specific amygdala areas relevant to understand the cSNC effect, suggesting follow-up experiments aimed at testing the function of these regions in reward downshift.

Choice Repetition Bias in Intertemporal Choice: An Eye‐Tracking Study

ABSTRACTIntertemporal choices (i.e., the choice between a sooner available but smaller reward and a later available but larger reward) were initially thought to reflect stable preferences for immediate or delayed rewards. However, recently, it has been shown that intertemporal choices are influenced by factors such as context variables and attentional processes. Here, we investigate if another factor, the choice repetition bias, affects decision making and attentional processes in intertemporal choice. The choice repetition bias is characterized by the tendency to repeat previous choices and to be slower when switching to an alternative choice. In a series of two experiments (including a preregistered, eye‐tracking study), we find that the choice repetition bias exists in intertemporal choice. We also find tentative support for an early attentional bias towards the favored attribute dimension of the previous choice; however, this effect disappears when taking the whole decision process into account. This finding raises interesting questions about the cognitive processes underlying the choice repetition bias. In addition, we successfully replicate other attentional effects from the intertemporal choice literature (e.g., more fixations on monetary dimension, gaze cascade effect).

Methylphenidate, but not citalopram, decreases impulsive choice in rats performing a temporal discounting task.

Drugs targeting monoamine systems remain the most common treatment for disorders with impulse control impairments. There is a body of literature suggesting that drugs affecting serotonin reuptake and dopamine reuptake can modulate distinct aspects of impulsivity - though such tests are often performed using distinct behavioral tasks prohibiting easy comparisons. Here, we directly compare pharmacologic agents that affect dopamine (methylphenidate) vs serotonin (citalopram) manipulations on choice impulsivity in a temporal discounting task where rats could choose between a small, immediate reward or a large reward delayed at either 2 or 10s. In control conditions, rats preferred the large reward at a small (2s) delay and discounted the large reward at a long (10s) delay. Methylphenidate, a dopamine transport inhibitor that blocks reuptake of dopamine, dose-dependently increased large reward preference in the long delay (10s) block. Citalopram, a selective serotonin reuptake inhibitor, had no effect on temporal discounting behavior. Impulsive behavior on the temporal discounting task was at least partially mediated by the nucleus accumbens shell. Bilateral lesions to the nucleus accumbens shell reduced choice impulsivity during the long delay (10s) block. Following lesions, methylphenidate did not impact impulsivity. Our results suggest that striatal dopaminergic systems modulate choice impulsivity via actions within the nucleus accumbens shell, whereas serotonin systems may regulate different aspects of behavioral inhibition/impulsivity.

Transfer between tasks involving frustrative nonreward in rats: From consummatory to instrumental successive negative contrast

In tasks involving frustrative nonreward, animals learn to expect a large reward and eventually the reward is unexpectedly (i.e., without signals) downshifted to a small reward. Rats exposed to such tasks exhibit a transient rejection of the reward (in consummatory successive negative contrast, cSNC), or a transient deterioration of anticipatory behavior (in instrumental successive negative contrast, iSNC). When these tasks are administered in series, animals trained first in the cSNC task exhibit a reduced iSNC effect. This cSNC-to-iSNC transfer effect has been attributed to counterconditioning learning during cSNC postshift sessions, that is, to pairings of anticipatory frustration (a negative emotional response) with a reward. This hypothesis was tested in two experiments that manipulated the number of postshift trials in a cSNC task (Phase 1) before switching animals to the iSNC task (Phase 2). In these experiments, animals that received a single downshift session in the cSNC task (Phase 1) exhibited a stronger iSNC effect (Phase 2) than animals that had received either five (Experiment 1) or eight (Experiment 2) downshift sessions. More extensive downshift experience created more opportunities to develop counterconditioning. These results lend support to a role of counterconditioning in the recovery from reward downshift and in the development of transfer effects across reward downshift tasks that differ in terms of response requirements, reward type, and contextual cues.

Chronic high-dose testosterone impairs economic decision making, but has no effect on memory in male rats

The goal is to understand consequences of anabolic-androgenic steroid (AAS) abuse on cognitive function, using rats as a model. Economic decision making was evaluated in an operant test of effort value discounting, where subjects choose between 2 levers that deliver large and small rewards differing in maximum value and reward contrast. The hypothesis is that chronic high-dose testosterone increases preference for large rewards. Male rats were treated chronically with testosterone (7.5 mg/kg) or vehicle. Initially, all rats preferred the large reward lever when large and small rewards remained fixed at 3 and 1 sugar pellets, respectively. When different reward values were introduced, and with increasing response requirements, testosterone-treated rats made fewer responses for the large reward, and increased omissions. They earned fewer rewards overall. To determine if testosterone impairs memory, rats were tested for recognition memory with the novel object recognition and social transmission of food preference tasks, and for spatial memory with the radial arm maze and Morris water maze. There was not effect of chronic high-dose testosterone on any memory task. These results suggest that testosterone shifts economic decision making towards larger rewards even when they are disadvantageous, but does not alter memory in rats.

Developmental exposure to 17-α-hydroxyprogesterone caproate disrupts decision-making in adult female rats: A potential role for a dopaminergic mechanism

The synthetic progestin, 17α-hydroxyprogesterone caproate (17-OHPC), is administered to pregnant individuals at risk for preterm birth and is likely transferred from mother to fetus. Yet, there is little information regarding the potential effects of 17-OHPC administration on behavioral and neural development in offspring. In rats, neonatal 17-OHPC exposure altered dopaminergic fiber distribution and density in the prelimbic medial prefrontal cortex (mPFC) in neonates and adolescents, respectively. Additionally, neonatal 17-OHPC exposure in male rats increased response omissions in a delay discounting task of impulsive decision-making. Because developmental 17-OHPC exposure has differential effects in males and females, investigating the effects of 17-OHPC on impulsive decision-making in female rats is necessary. The present study tested the effects of developmental 17-OHPC exposure (P1–P14) in a delay discounting task in which female rats chose between a small immediate reward and a larger delayed (0, 15 30, or 45 s) reward. 17-OHPC-exposed females made more omissions than controls. There was no effect of 17-OHPC on large reward preference nor on response time, and omissions were similar during both free- and forced-choice trials. The present study also aimed to investigate the neural mechanisms underlying omissions in 17-OHPC-exposed female rats. The dopamine transporter inhibitor, methylphenidate (MPH), was administered prior to delay discounting testing. MPH treatment did not reduce omissions in 17-OHPC-exposed females. If anything, MPH increased omissions in control females nearly fourfold during the longest delays. These results suggest that developmental 17-OHPC exposure increased omissions without affecting impulsivity or slowing decision-making. Furthermore, omissions may be regulated, at least in part, by dopaminergic mechanisms.

Choice impulsivity after repeated social stress is associated with increased perineuronal nets in the medial prefrontal cortex

Repeated stress can predispose to substance abuse. However, behavioral and neurobiological adaptations that link stress to substance abuse remain unclear. This study investigates whether intermittent social defeat (ISD), a stress protocol that promotes drug-seeking behavior, alters intertemporal decision-making and cortical inhibitory function in the medial prefrontal cortex (mPFC). Male long evans rats were trained in a delay discounting task (DDT) where rats make a choice between a fast (1 s) small reward (1 sugar pellet) and a large reward (3 sugar pellets) that comes with a time delay (10 s or 20 s). A decreased preference for delayed rewards was used as an index of choice impulsivity. Rats were exposed to ISD and tested in the DDT 24 h after each stress episode, and one- and two-weeks after the last stress episode. Immunohistochemistry was performed in rat’s brains to evaluate perineuronal nets (PNNs) and parvalbumin GABA interneurons (PV) labeling as markers of inhibitory function in mPFC. ISD significantly decreased the preference for delayed large rewards in low impulsive, but not high impulsive, animals. ISD also increased the density of PNNs in the mPFC. These results suggest that increased choice impulsivity and cortical inhibition predispose animals to seek out rewards after stress.

Instrumental successive negative contrast in rats: Trial distribution, reward magnitude, and prefrontal cortex activation

Successive negative contrast (SNC) has been used to study reward relativity, reward loss, and frustration for decades. In instrumental SNC (iSNC), the anticipatory performance of animals downshifted from a large reward to a small reward is compared to that of animals always reinforced with the small reward. iSNC involves a transient deterioration of anticipatory behavior in downshifted animals compared to unshifted controls. There is scattered information on the optimal parameters to produce this effect and even less information about its neural basis. Five experiments with rats trained in a runway to collect food pellets explored the effects of trial distribution (massed or spaced), amount of preshift training, reward disparity, and reward magnitude on the development of an iSNC effect. Start, run, and goal latencies were measured. Using spaced trials (one trial per day), evidence of the iSNC effect was observed with 24 preshift trials and a 32-to-4 pellet disparity. With massed trials (4 trials per session separated by 30-s intertrial intervals), evidence of iSNC was found with 12 preshift sessions (a total of 48 trials) and a 16-to-2 pellet disparity. The massed-training procedure was then used to assess neural activity in three prefrontal cortex areas using c-Fos expression in animals perfused after the first downshift session. There was evidence of increased activation in the anterior cingulate cortex and a trend toward increased activation in the infralimbic and prelimbic cortices. These procedures open a venue for studying the neural basis of the instrumental behavior of animals that experience reward loss.

Evaluation of a financial incentive intervention on malaria prevalence among the residents in Lake Victoria basin, Kenya: study protocol for a cluster-randomized controlled trial

BackgroundIn the Lake Victoria basin of western Kenya, malaria remains highly endemic despite high coverage of interventions such as mass distribution of long-lasting insecticidal nets (LLIN), indoor residual spraying (IRS) programs, and improvement of availability and accessibility of rapid diagnostic tests (RDT) and artemisinin-based combination therapy (ACT) at community healthcare facilities. We hypothesize that one major cause of the residual transmission is the lack of motivation among residents for malaria prevention and early treatment.MethodsThis study will aim to develop a demand-side policy tool to encourage local residents’ active malaria prevention and early treatment-seeking behaviors. We examine the causal impact of a financial incentive intervention complemented with malaria education to residents in malaria-prone areas. A cluster-randomized controlled trial is designed to assess the effect of the financial incentive intervention on reducing malaria prevalence in residents of Suba South in Homa Bay County, Kenya. The intervention includes two components. The first component is the introduction of a financial incentive scheme tied to negative RDT results for malaria infection among the target population. This study is an attempt to promote behavioral changes in the residents by providing them with monetary incentives. The project has two different forms of incentive schemes. One is a conditional cash transfer (CCT) that offers a small reward (200 Ksh) for non-infected subjects during the follow-up survey, and the other is a lottery incentive scheme (LIS) that gives a lottery with a 10% chance of winning a large reward (2000 Ksh) instead of the small reward. The second component is a knowledge enhancement with animated tablet-based malaria educational material (EDU) developed by the research team. It complements the incentive scheme by providing the appropriate knowledge to the residents for malaria elimination. We evaluate the intervention’s impact on the residents’ malaria prevalence using a cluster-randomized control trial.DiscussionA policy tool to encourage active malaria prevention and early treatment to residents in Suba South, examined in this trial, may benefit other malaria-endemic counties and be incorporated as part of Kenya’s national malaria elimination strategy.Trial registrationUMIN000047728. Registered on 29th July 2022.

Weak Signal Asymptotics for Sequentially Randomized Experiments

We use the lens of weak signal asymptotics to study a class of sequentially randomized experiments, including those that arise in solving multiarmed bandit problems. In an experiment with n time steps, we let the mean reward gaps between actions scale to the order [Formula: see text] to preserve the difficulty of the learning task as n grows. In this regime, we show that the sample paths of a class of sequentially randomized experiments—adapted to this scaling regime and with arm selection probabilities that vary continuously with state—converge weakly to a diffusion limit, given as the solution to a stochastic differential equation. The diffusion limit enables us to derive refined, instance-specific characterization of stochastic dynamics and to obtain several insights on the regret and belief evolution of a number of sequential experiments including Thompson sampling (but not upper-confidence bound, which does not satisfy our continuity assumption). We show that all sequential experiments whose randomization probabilities have a Lipschitz-continuous dependence on the observed data suffer from suboptimal regret performance when the reward gaps are relatively large. Conversely, we find that a version of Thompson sampling with an asymptotically uninformative prior variance achieves near-optimal instance-specific regret scaling, including with large reward gaps, but these good regret properties come at the cost of highly unstable posterior beliefs. This paper was accepted by Baris Ata, stochastic models and simulation. Supplemental Material: The data and online appendix are available at https://doi.org/10.1287/mnsc.2023.4964 .

Longitudinal associations of volunteering, grandparenting, and family care with processing speed: A gender perspective on prosocial activity and cognitive aging in the second half of life.

An active lifestyle has been associated with better cognitive performance in many studies. However, most studies have focused on leisure activities or paid work, with less consideration of the kind of prosocial activities, many people engage in, including volunteering, grandparenting, and family care. In the present study, based on four waves of the German Ageing Survey (N = 6,915, aged 40-85 at baseline), we used parallel growth curves to investigate the longitudinal association of level and change in volunteering, grandparenting, and family care with level and change in processing speed. Given the gendered nature of engagement in these activities over the life span, we tested for gender differences in the associations. Only volunteering was reliably associated with higher speed of processing at baseline, no consistent longitudinal associations were found. Our results show that although prosocial activities are of great societal importance, expectations of large rewards in terms of cognitive health may be exaggerated. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Electrocortical correlates of hypersensitivity to large immediate rewards in sensation seeking

Sensation seeking and delay discounting are strong predictors of various risk-taking behaviors. However, the relationship between sensation seeking and delay discounting remains elusive. Here, we addressed this issue by examining how high sensation seekers (HSS; N = 40) and low sensation seekers (LSS; N = 40) evaluated immediate and delayed rewards with low and high amounts during a behavioral task and an EEG task of delay discounting. Although HSS and LSS exhibited comparable discounting preference at the behavioral level, HSS relative to LSS was associated with a greater delay discounting effect at the neural level when earned rewards were large. This abnormality of reward magnitude was further corroborated by an electrocortical hypersensitivity to large immediate rewards and a stronger neural coding of reward magnitude for HSS as compared to LSS. Our findings support both the hyperactive approach theory and the optimal arousal theory in sensation seeking and have implications for the prevention and intervention targeting sensation seeking to reduce maladaptive risk-taking behaviors.

SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN INVESTASI SAHAM SYARIAH DALAM INDEKS JII 70 MENGGUNAKAN METODE AHP BESERTA PERHITUNGAN MONEY MANAGEMENT

<p align="justify"><span class="fontstyle0">Abstract : </span><span class="fontstyle2">Stock investment is an investment activity by purchasing a stock in the hope of getting a large enough reward, but it is important to note that stock investment is an activity that has the same risk and reward. Since the Covid-19, the number of single investor identification is increasing, but there are still many novice investors who are confused about which sector to start investing in and which company to choose as an investment as well and how to put capital with their goal. This research is one step to help novice investors find out which companies are<br />suitable to be chosen using the AHP method, supported by several company financial reports. And this research, the Money Management feature is added to make it easier for investors to allocate the funds they want to invest according to their goals. With the AHP method, the company's financial statements that were previously standard<br />and unstructured have turned into structured and directed so that novice investors who use this application can get a view on choosing the best stock based on the results of the highest ranking value and also the investors with this application get help with money management simulation by prioritizing averaging techniques so that the return they are get can be maximized.</span> <br /><br /></p>

Energy Efficient Power Allocation in Massive MIMO Based on Parameterized Deep DQN

Machine learning offers advanced tools for efficient management of radio resources in modern wireless networks. In this study, we leverage a multi-agent deep reinforcement learning (DRL) approach, specifically the Parameterized Deep Q-Network (DQN), to address the challenging problem of power allocation and user association in massive multiple-input multiple-output (M-MIMO) communication networks. Our approach tackles a multi-objective optimization problem aiming to maximize network utility while meeting stringent quality of service requirements in M-MIMO networks. To address the non-convex and nonlinear nature of this problem, we introduce a novel multi-agent DQN framework. This framework defines a large action space, state space, and reward functions, enabling us to learn a near-optimal policy. Simulation results demonstrate the superiority of our Parameterized Deep DQN (PD-DQN) approach when compared to traditional DQN and RL methods. Specifically, we show that our approach outperforms traditional DQN methods in terms of convergence speed and final performance. Additionally, our approach shows 72.2% and 108.5% improvement over DQN methods and the RL method, respectively, in handling large-scale multi-agent problems in M-MIMO networks.