Network slicing is a key technology in 5G communications system. Its purpose is to dynamically and efficiently allocate resources for diversified services with distinct requirements over a common underlying physical infrastructure. Therein, demand-aware resource allocation is of significant importance to network slicin…
Replicates and improves Uniswap V3 model using DDQN and Mamba.
problem Improving liquidity provision in Uniswap V3 with reinforcement learning.
method Combines DDQN with Mamba and introduces a new reward function.
result Shows stronger theoretical support and better performance than original model.
With the increasing complexity of modern power systems, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the WECC composite load model (WECC CLM) has shown to effectively capture the dynamic load re…
Agents learn to outperform in trading by using past and current prices.
problem Optimal trading performance beyond theoretical limits.
method Two-agent Almgren-Chriss liquidation game, schedule-learning, DDQN architectures.
result Agents with access to past and current prices achieve supra-competitive outcomes.
We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance, in deep-Q networks (DQN), the Q-value is a linear function of the feature repres…
Paper uses DDQN for trading assets, showing better performance than market benchmarks.
problem Improving financial trading strategies using AI.
method Double Deep Q-Network (DDQN) algorithm for trading multiple assets.
result Trading agent outperformed market benchmarks and achieved higher net asset value.
Deep Q-Learning system for straddle options in volatile markets.
problem High computational costs and unstable performance in high-volatility markets.
method Attention mechanisms in Transformer-DDQN, novel reward function, and resistance level identification.
result Transformer-DDQN model exhibits lowest maximum drawdown and highest average return.
AI algorithms outperform traditional trading methods in stock markets.
problem Traditional trading methods struggle with risk management and edge over classical approaches.
method Used Deep Reinforcement Learning (DRL) algorithms (DDQN and PPO) to compare with Buy and Hold benchmark.
result DRL algorithms provide a substantial edge over classical approaches in terms of risk-adjusted returns.
Dynamic cell-free networks reduce complexity in serving many devices with distributed APs and DRL.
problem Designing efficient cell-free networks with many devices and APs.
method Dynamic architecture, SIC, DAS, DRL for optimization.
result DRL significantly improves performance in dynamic cell-free networks.
Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to discover them on their own without any supervision beyond these sparse rewards. W…
Uses news sentiment scores for direct reinforcement trading in financial markets.
problem Incorporating news data into quantitative trading remains challenging.
method Directly uses news sentiment scores and raw data as inputs for reinforcement learning, processed by sequence models.
result Achieves superior performance compared to market benchmarks.
New hybrid model combines GARCH and reinforcement learning for improved VaR estimation.
problem Inaccurate VaR estimation in volatile financial markets.
method Combines GARCH volatility models with DDQN reinforcement learning for dynamic risk forecasting.
result Significant improvement in VaR accuracy and reduction in breaches.
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences. Action grammars is the parallel idea, that there is an underlying set of rules (a "grammar") that govern how we hierarchically combine actions to form new, more complex actions. We introduce the Action Grammar Re…
Study analyzes sensitivity of RL algorithm for ICU hemodynamic management.
problem Evaluating safety and reliability of RL in clinical settings.
method Sensitivity analysis of Duel-DDQN on ICU sepsis patients.
result RL policies are sensitive to various implementation factors.
This paper makes one step forward towards characterizing a new family of \textit{model-free} Deep Reinforcement Learning (DRL) algorithms. The aim of these algorithms is to jointly learn an approximation of the state-value function (V), alongside an approximation of the state-action value function (Q). Our analysis…
UAVs learn to collect data from IoT sensors efficiently.
problem Efficient UAV path planning for wireless data collection.
method Deep reinforcement learning (DDQN) with experience replay and convolutional layers.
result UAV control policy generalizes over changing scenario parameters.
A simple DQN-based multi-agent RL system for binary actions.
problem Complexity and training issues in multi-agent reinforcement learning.
method Shared state and rewards, agent-specific actions, experience replay pool.
result Better performance and faster convergence compared to conventional methods.
RAmmStein optimizes liquidity management in AMMs by learning to rebalance efficiently.
problem Optimal control of concentrated liquidity in decentralized exchanges.
method Formulates as an optimal control problem, uses Deep Reinforcement Learning with HJB-QVI.
result Achieves highest net ROI (1.60%) compared to greedy strategies, reduces rebalancing frequency by 85%.
A meta-learning approach for efficient algorithm selection in budget-limited scenarios.
problem Efficiently selecting the best-performing machine learning algorithm with limited computational resources.
method A Markov Decision Process framework where an agent decides whether to train, wake up, or start new algorithms based on partial learning curves.
result Meta-learning from learning curves improves algorithm selection, especially when learning curves do not intersect frequently.