Co-DQL improves traffic signal control using multi-agent reinforcement learning.
problem Optimizing signal timing for large-scale traffic control.
method Cooperative double Q-learning (Co-DQL) with mean field approximation and reward allocation.
result Co-DQL reduces average waiting time for vehicles in the road system.
Double Q-learning has the same mean-squared error as Q-learning under certain conditions.
problem Comparing the mean-squared error of Double Q-learning and Q-learning.
method Theoretical analysis based on Lyapunov equations for both tabular and linear function approximation settings.
result The asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning under specific conditions.
Introduces LTQL for factored policies in cooperative MARL.
problem Learning optimal joint policies in collaborative MARL scenarios.
method Logical Team Q-learning (LTQL) as a stochastic approximation to dynamic programming.
result LTQL provides factored policies for optimal joint behavior in cooperative MARL.
Study shows market makers can cooperate without communication.
problem Concerns of collusion in AI-driven market-making.
method Formulated as a repeated game, studied with Q-learning.
result Market makers can learn cooperative strategies without communication.
Proposes a new Deep Recurrent Double Q-Learning model for Atari games.
problem Improving Deep Reinforcement Learning models for Atari games.
method Integrates Double Q-Learning and Recurrent Networks (LSTM, DRQN) for Atari games.
result Demonstrates improved performance in Atari games compared to existing models.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
problem Underestimation bias in double Q-learning leading to non-optimal fixed points.
method Proposes a simple approach using approximate dynamic programming to bound the target value.
result Significant improvement in learning performance over baseline algorithms in Atari benchmark tasks.
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
problem Understanding and improving the convergence of multi-agent Q-learning with value factorization.
method Formalized a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning.
result Multi-agent Q-learning with linear value factorization can converge under certain conditions.
Paper analyzes finite-time convergence of double Q-learning.
problem Overestimation issue in Q-learning.
method Finite-time analysis of double Q-learning.
result Convergence to ε-accurate neighborhood in finite iterations.
MaxMax Q-Learning improves coordination in multi-agent reinforcement learning by refining action selection.
problem Relative over-generalization in decentralized multi-agent reinforcement learning.
method MaxMax Q-Learning employs iterative sampling and evaluation of potential next states to refine approximations of ideal state transitions.
result MaxMax Q-Learning frequently outperforms existing baselines, demonstrating enhanced convergence and sample efficiency.
EBQL reduces bias in Q-learning for improved performance.
problem Over- and under-estimation biases in Q-learning degrade performance.
method Ensemble Bootstrapping to reduce both over- and under-estimation biases.
result EBQL outperforms other Q-learning methods in Atari games.
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
problem Underestimation bias in deep actor-critic methods for reinforcement learning.
method Introduces a parameter-free Q-learning variant that combines maximum and minimum operators to bound value estimates.
result Improves state-of-the-art performance on OpenAI Gym tasks.
Paper develops MFC approach to reduce MARL complexity.
problem Curse of dimensionality in cooperative MARL.
method Mean-field control (MFC) and Q-learning.
result Linear convergence rate for MFC-K-Q, independent of N N N . GUM tackles MARL by avoiding overestimation through state-marginal restriction.
problem Overestimation of values in large joint state-action spaces.
method Greedy UnMixing through state-marginal restriction and unmixing.
result Superior performance compared to existing Q-learning and general MARL algorithms.
New algorithm learns efficiently in multi-agent settings.
problem Efficient learning in multi-agent Markov decision processes.
method Cooperative Prioritized Sweeping: model-based reinforcement learning with sample efficiency.
result Outperforms state-of-the-art on SysAdmin and randomized environments.
A MARL system improves productivity on a metallurgical pickling line.
problem Improving productivity on a metallurgical pickling line.
method Combines mathematical modeling and Multi-Agent Reinforcement Learning (MARL).
result Significant improvement in automation systems.
Boosts Q-learning by using value function bounds.
problem Efficiently solving new tasks using past experience.
method Derives double-sided bounds on optimal value function and uses them to update Q-function.
result Boosted training performance through alternative Q-function update method.
SAVE combines Q-learning and MCTS with amortized value estimates for improved performance.
problem Combining model-free Q-learning and model-based MCTS for efficient learning and planning.
method SAVE uses a learned prior to guide MCTS, which estimates improved state-action values. These estimates are used to update the prior, creating a cooperative relationship between learning and search.
result SAVE achieves higher rewards with fewer training steps and strong performance with small search budgets.
Reverse Experience Replay improves Deep Q-learning for sparse rewards.
problem Sparse rewards and reward-maximizing tasks in Deep Q-learning.
method Sampling transitions in reverse order for training.
result Significantly increased performance in tasks with limited experience and memory capacity.
Hierarchical MARL learns complementary skills for team coordination.
problem Creating intelligent agents that coordinate like human sports teams.
method Two-level hierarchical MARL with unsupervised skill discovery.
result Emergence of useful and complementary skills in team games.
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
Temporal-difference (TD) learning is an important field in reinforcement learning. Sarsa and Q-Learning are among the most used TD algorithms. The Q( σ σ σ ) algorithm (Sutton and Barto (2017)) unifies both. This paper extends the Q( σ σ σ ) algorithm to an online multi-step algorithm Q( σ , λ σ, λ σ , λ ) using eligibility traces and int…
Optimal trade execution is an important problem faced by essentially all traders. Much research into optimal execution uses stringent model assumptions and applies continuous time stochastic control to solve them. Here, we instead take a model free approach and develop a variation of Deep Q-Learning to estimate the opt…
FACMAC combines deep policy gradients with factored critic for multi-agent reinforcement learning.
problem Cooperative multi-agent reinforcement learning in discrete and continuous action spaces.
method FACMAC uses a centralised but factored critic, combining per-agent utilities into a joint action-value function.
result FACMAC outperforms MADDPG and other baselines on multi-agent particle environments and StarCraft II tasks.
RL agent learns to place limit orders for trading signals in financial markets.
problem Training an RL agent to execute trading signals in limit order book markets.
method Deep Duelling Double Q-learning with APEX architecture, using synthetic alpha signals.
result RL agent outperforms heuristic trading strategies in inventory management and order placing.
Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.
problem Inefficiency and instability of DDPG in practical applications, and difficulty in controlling Q estimation bias and variance.
method Introduces a Regularly Updated Deterministic (RUD) policy gradient algorithm.
result The RUD algorithm makes better use of new data and has lower Q value variance, leading to improved performance.
A two-stream reinforcement learning model improves decision-making across human and neuropsychiatric studies.
problem Improving reinforcement learning models to better simulate human decision-making and neuropsychiatric conditions.
method Proposes a two-stream reinforcement learning model that processes positive and negative rewards and incorporates reward-processing biases.
result The two-stream model outperforms standard Q-learning and SARSA methods on various tasks and datasets.
A new framework uses DDQN to simplify WECC CLM for efficient load modeling.
problem Complexity and high parameter count in WECC CLM.
method Two-stage approach with DDQN for load composition and parameter selection.
result The framework efficiently approximates WECC CLM transient responses.
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the cr…
Improved Q-learning with hindsight factor reduces overestimation errors.
problem Overestimation errors in Q-learning leading to suboptimal policies.
method Introducing a hindsight factor as an additional loss term in Q-learning.
result The hindsight factor significantly reduces overestimation errors and improves stability.
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules…
Loyal buyer-seller relationships can arise by design, e.g. when a seller tailors a product to a specific market niche to accomplish the best possible returns, and buyers respond to the dedicated efforts the seller makes to meet their needs. We ask whether it is possible, instead, for loyalty to arise spontaneously, and…
Reduces overestimation bias in multi-agent RL, improving performance.
problem Value function overestimation bias in multi-agent RL.
method Double centralized critics to reduce overestimation bias.
result Significant improvement in performance on mixed tasks.
Optimizes mobile notifications for multiple objectives using reinforcement learning.
problem Optimizing mobile notification systems for multiple objectives.
method End-to-end offline reinforcement learning with Double Deep Q-network and Conservative Q-learning.
result Demonstrates improved performance and benefits of the proposed approach.
Improved Q-learning for multi-agent reinforcement learning by weighting joint action values.
problem QMIX restricts Q Q Q -values to monotonic mixtures, limiting complex value functions. method Introduced weighted projection to recover optimal policies, improving performance.
result CW QMIX and OW QMIX outperform baseline QMIX on multi-agent tasks.
Paper uses RL to optimize trading in time-varying liquidity markets.
problem Optimal execution in dynamic liquidity markets.
method Double Deep Q-learning for neural networks.
result Trained RL algorithm learns optimal trading policies in time-varying liquidity.
Develops methods for cooperative Bayesian inference.
problem Cooperation between learning agents.
method Sequential Bayesian inference approaches.
result Theoretical foundation for cooperative inference.
Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (…
The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator. Surprisingly, despite these concerns, and independent of its effect on explorati…
Multi-cell cooperative processing with limited backhaul traffic is studied for cellular uplinks. Aiming at reduced backhaul overhead, a sparsity-regularized multi-cell receive-filter design problem is formulated. Both unstructured distributed cooperation as well as clustered cooperation, in which base station groups ar…
Develops an equilibrium model for securities pricing in a mixed cooperative and non-cooperative market.
problem Equilibrium pricing of securities in a market with cooperative and non-cooperative agents.
method Conditional extended mean-field control for cooperative agents, mean-field model for both cooperative and non-cooperative agents.
result Existence of a unique equilibrium for both finite-agent and mean-field models under certain conditions.
Paper analyzes Q-learning with neural networks, proving a fast convergence rate.
problem Analyzing the convergence rate of neural Q-learning.
method Finite-time analysis of neural Q-learning with a deep ReLU network.
result Neural Q-learning converges to optimal policy with O ( 1 / T ) O(1/\sqrt{T}) O ( 1/ T ) rate. DE-QT detects optimal Q-learning stopping points.
problem Information loss in Q-learning during prolonged training.
method Introducing DE-QT to detect entropy changes in Q-tables.
result DE-QT identifies the best stopping point for Q-learning.
This paper analyzes momentum Q-learning with finite-sample guarantees.
problem Improving Q-learning performance with momentum schemes.
method Proposes MomentumQ algorithm integrating Nesterov and Polyak's momentum schemes, analyzes convergence for function approximations.
result Establishes finite-sample convergence rates for MomentumQ, demonstrating better performance than vanilla Q-learning.
PQ-learning improves Q-learning by periodically updating target estimates.
problem Improving sample complexity in Q-learning for finding optimal policies.
method Maintains two Q-value estimates, one online and one target, updated periodically.
result PQ-learning achieves better sample complexity for finding epsilon-optimal policies.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
Linear Q-learning converges to a bounded set without divergence.
problem Proving linear Q-learning does not diverge and converges to a bounded set.
method No modifications to the original linear Q-learning algorithm, no Bellman completeness or near-optimality assumptions, only an ε-softmax behavior policy with adaptive temperature.
result First L 2 L^2 L 2 convergence rate of linear Q-learning iterates to a bounded set. Stable cooperation emerges in fluctuating environments.
problem Evolutionary stability of cooperation in fluctuating conditions.
method Agents with fluctuating wealth share public goods, leading to cooperation.
result Agents with cooperation produce an advantage in fluctuating environments.
Mathematical framework for cooperative communication explains belief transmission.
problem Lack of understanding why cooperation enables effective belief transmission.
method Connection to optimal transport theory, deriving prior models, statistical interpretations, proofs of robustness and instability.
result Cooperative communication provably enables effective, robust belief transmission.