Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved impressive results, typically in homogeneous scenarios. However, heterogeneous scenarios are also very common and usually harder to solve. In this paper, we mainly discuss cooperative heterogeneous MARL problems in Starcraft Multi-Agent Challenges (SMAC) environment. We firstly define and describe the heterogeneous problems in SMAC. In order to comprehensively reveal and study the problem, we make new maps added to the original SMAC maps. We find that baseline algorithms fail to perform well in those heterogeneous maps. To address this issue, we propose the Grouped Individual-Global-Max Consistency (GIGM) and a novel MARL algorithm, Grouped Hybrid Q Learning (GHQ). GHQ separates agents into several groups and keeps individual parameters for each group, along with a novel hybrid structure for factorization. To enhance coordination between groups, we maximize the Inter-group Mutual Information (IGMI) between groups' trajectories. Experiments on original and new heterogeneous maps show the fabulous performance of GHQ compared to other state-of-the-art algorithms.
In this paper we pursue the question of a fully online trading algorithm (i.e. one that does not need offline training on previously gathered data). For this task we use Double Deep $Q$-learning in the episodic setting with Fast Learning Networks approximating the expected reward $Q$. Additionally, we define the possible terminal states of an episode in such a way as to introduce a mechanism to conserve some of the money in the trading pool when market conditions are seen as unfavourable. Some of these money are taken as profit and some are reused at a later time according to certain criteria. After describing the algorithm, we test it using the 1-minute-tick data for Cardano's price on Binance. We see that the agent performs better than trading with randomly chosen actions on each timestep. And it does so when tested on the whole dataset as well as on different subsets, capturing different market trends.
Nash Q-learning may be considered one of the first and most known algorithms in multi-agent reinforcement learning (MARL) for learning policies that constitute a Nash equilibrium of an underlying general-sum Markov game. Its original proof provided asymptotic guarantees and was for the tabular case. Recently, finite-sample guarantees have been provided using more modern RL techniques for the tabular case. Our work analyzes Nash Q-learning using linear function approximation -- a representation regime introduced when the state space is large or continuous -- and provides finite-sample guarantees that indicate its sample efficiency. We find that the obtained performance nearly matches an existing efficient result for single-agent RL under the same representation and has a polynomial gap when compared to the best-known result for the tabular case.
Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states. Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theoretical analysis of the resulting properties of the algorithms. In this work, we show that using this regularizer under a mixture distribution of the policy and the expert provides a particularly illuminating perspective: the original objective can be understood as squared Bellman error minimization, and the corresponding optimization problem minimizes a bounded $\chi^2$-Divergence between the expert and the mixture distribution. This perspective allows us to address instabilities and properly treat absorbing states. We show that our method, Least Squares Inverse Q-Learning (LS-IQ), outperforms state-of-the-art algorithms, particularly in environments with absorbing states. Finally, we propose to use an inverse dynamics model to learn from observations only. Using this approach, we retain performance in settings where no expert actions are available.
Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is greater than a given value. The algorithm can be seen as an extension of the value iteration algorithm. We also show how the proposed algorithm could be generalized to use neural networks, similarly to the deep Q learning extension of Q learning.
We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation, we extend the distributionally robust $Q$-learning framework studied in Liu et al. [2022]. Further, we improve the design and analysis of their multi-level Monte Carlo estimator. Assuming access to a simulator, we prove that the worst-case expected sample complexity of our algorithm to learn the optimal robust $Q$-function within an $\epsilon$ error in the sup norm is upper bounded by $\tilde O(|S||A|(1-\gamma)^{-5}\epsilon^{-2}p_{\wedge}^{-6}\delta^{-4})$, where $\gamma$ is the discount rate, $p_{\wedge}$ is the non-zero minimal support probability of the transition kernels and $\delta$ is the uncertainty size. This is the first sample complexity result for the model-free robust RL problem. Simulation studies further validate our theoretical results.
In this paper, a Gauss-Newton Temporal Difference (GNTD) learning method is proposed to solve the Q-learning problem with nonlinear function approximation. In each iteration, our method takes one Gauss-Newton (GN) step to optimize a variant of Mean-Squared Bellman Error (MSBE), where target networks are adopted to avoid double sampling. Inexact GN steps are analyzed so that one can safely and efficiently compute the GN updates by cheap matrix iterations. Under mild conditions, non-asymptotic finite-sample convergence to the globally optimal Q function is derived for various nonlinear function approximations. In particular, for neural network parameterization with relu activation, GNTD achieves an improved sample complexity of $\tilde{\mathcal{O}}(\varepsilon^{-1})$, as opposed to the $\mathcal{\mathcal{O}}(\varepsilon^{-2})$ sample complexity of the existing neural TD methods. An $\tilde{\mathcal{O}}(\varepsilon^{-1.5})$ sample complexity of GNTD is also established for general smooth function approximations. We validate our method via extensive experiments in several RL benchmarks, where GNTD exhibits both higher rewards and faster convergence than TD-type methods.
We study optimality for the safety-constrained Markov decision process which is the underlying framework for safe reinforcement learning. Specifically, we consider a constrained Markov decision process (with finite states and finite actions) where the goal of the decision maker is to reach a target set while avoiding an unsafe set(s) with certain probabilistic guarantees. Therefore the underlying Markov chain for any control policy will be multichain since by definition there exists a target set and an unsafe set. The decision maker also has to be optimal (with respect to a cost function) while navigating to the target set. This gives rise to a multi-objective optimization problem. We highlight the fact that Bellman's principle of optimality may not hold for constrained Markov decision problems with an underlying multichain structure (as shown by the counterexample due to Haviv. We resolve the counterexample by formulating the aforementioned multi-objective optimization problem as a zero-sum game and thereafter construct an asynchronous value iteration scheme for the Lagrangian (similar to Shapley's algorithm). Finally, we consider the reinforcement learning problem for the same and construct a modified $Q$-learning algorithm for learning the Lagrangian from data. We also provide a lower bound on the number of iterations required for learning the Lagrangian and corresponding error bounds.
We present Q-Cogni, an algorithmically integrated causal reinforcement learning framework that redesigns Q-Learning with an autonomous causal structure discovery method to improve the learning process with causal inference. Q-Cogni achieves optimal learning with a pre-learned structural causal model of the environment that can be queried during the learning process to infer cause-and-effect relationships embedded in a state-action space. We leverage on the sample efficient techniques of reinforcement learning, enable reasoning about a broader set of policies and bring higher degrees of interpretability to decisions made by the reinforcement learning agent. We apply Q-Cogni on the Vehicle Routing Problem (VRP) and compare against state-of-the-art reinforcement learning algorithms. We report results that demonstrate better policies, improved learning efficiency and superior interpretability of the agent's decision making. We also compare this approach with traditional shortest-path search algorithms and demonstrate the benefits of our causal reinforcement learning framework to high dimensional problems. Finally, we apply Q-Cogni to derive optimal routing decisions for taxis in New York City using the Taxi & Limousine Commission trip record data and compare with shortest-path search, reporting results that show 85% of the cases with an equal or better policy derived from Q-Cogni in a real-world domain.
One of the key tasks in the economy is forecasting the economic agents' expectations of the future values of economic variables using mathematical models. The behavior of mathematical models can be irregular, including chaotic, which reduces their predictive power. In this paper, we study the regimes of behavior of two economic models and identify irregular dynamics in them. Using these models as an example, we demonstrate the effectiveness of evolutionary algorithms and the continuous deep Q-learning method in combination with Pyragas control method for deriving a control action that stabilizes unstable periodic trajectories and suppresses chaotic dynamics. We compare qualitative and quantitative characteristics of the model's dynamics before and after applying control and verify the obtained results by numerical simulation. Proposed approach can improve the reliability of forecasting and tuning of the economic mechanism to achieve maximum decision-making efficiency.
A robust auto-landing problem of a Truss-braced Wing (TBW) regional jet aircraft with poor stability characteristics is presented in this study employing a Fuzzy Reinforcement Learning scheme. Reinforcement Learning (RL) has seen a recent surge in practical uses in control systems. In contrast to many studies implementing Deep Learning in RL algorithms to generate continuous actions, the methodology of this study is straightforward and avoids complex neural network architectures by applying Fuzzy rules. An innovative, agile civil aircraft is selected not only to meet future aviation community expectations but also to demonstrate the robustness of the suggested method. In order to create a multi-objective RL environment, a Six-degree-of-freedom (6-DoF) simulation is first developed. By transforming the auto-landing problem of the aircraft into a Markov Decision Process (MDP) formulation, the problem is solved by designing a low-level Fuzzy Q-learning (FQL) controller. More specifically, the well-known Q-learning method, which is a discrete RL algorithm, is supplemented by Fuzzy rules to provide continuous actions with no need to complex learning structures. The performance of the proposed system is then evaluated by extensive flight simulations in different flight conditions considering severe wind gusts, measurement noises, actuator faults, and model uncertainties. Besides, the controller effectiveness would be compared with existing competing techniques such as Dynamic Inversion (DI) and Q-learning. The simulation results indicate the superior performance of the proposed control system as a reliable and robust control method to be employed in real applications.
Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains due to, for example, their instability in training. Therefore, in this paper, we adapt the soft-actor-critic (SAC) algorithm to the text-based environment. To deal with sparse extrinsic rewards from the environment, we combine it with a potential-based reward shaping technique to provide more informative (dense) reward signals to the RL agent. We apply our method to play difficult text-based games. The SAC method achieves higher scores than the Q-learning methods on many games with only half the number of training steps. This shows that it is well-suited for text-based games. Moreover, we show that the reward shaping technique helps the agent to learn the policy faster and achieve higher scores. In particular, we consider a dynamically learned value function as a potential function for shaping the learner's original sparse reward signals.
In recent years, large amounts of electronic health records (EHRs) concerning chronic diseases, such as cancer, diabetes, and mental disease, have been collected to facilitate medical diagnosis. Modeling the dynamic properties of EHRs related to chronic diseases can be efficiently done using dynamic treatment regimes (DTRs), which are a set of sequential decision rules. While Reinforcement learning (RL) is a widely used method for creating DTRs, there is ongoing research in developing RL algorithms that can effectively handle large amounts of data. In this paper, we present a novel approach, a distributed Q-learning algorithm, for generating DTRs. The novelties of our research are as follows: 1) From a methodological perspective, we present a novel and scalable approach for generating DTRs by combining distributed learning with Q-learning. The proposed approach is specifically designed to handle large amounts of data and effectively generate DTRs. 2) From a theoretical standpoint, we provide generalization error bounds for the proposed distributed Q-learning algorithm, which are derived within the framework of statistical learning theory. These bounds quantify the relationships between sample size, prediction accuracy, and computational burden, providing insights into the performance of the algorithm. 3) From an applied perspective, we demonstrate the effectiveness of our proposed distributed Q-learning algorithm for DTRs by applying it to clinical cancer treatments. The results show that our algorithm outperforms both traditional linear Q-learning and commonly used deep Q-learning in terms of both prediction accuracy and computation cost.
We present a new family of logit-Q dynamics for efficient learning in stochastic games by combining the log-linear learning (also known as logit dynamics) for the repeated play of normal-form games with Q-learning for unknown Markov decision processes within the auxiliary stage-game framework. In this framework, we view stochastic games as agents repeatedly playing some stage game associated with the current state of the underlying game while the agents' Q-functions determine the payoffs of these stage games. We show that the logit-Q dynamics presented reach (near) efficient equilibrium in stochastic teams with unknown dynamics and quantify the approximation error. We also show the rationality of the logit-Q dynamics against agents following pure stationary strategies and the convergence of the dynamics in stochastic games where the stage-payoffs induce potential games, yet only a single agent controls the state transitions beyond stochastic teams. The key idea is to approximate the dynamics with a fictional scenario where the Q-function estimates are stationary over epochs whose lengths grow at a sufficiently slow rate. We then couple the dynamics in the main and fictional scenarios to show that these two scenarios become more and more similar across epochs due to the vanishing step size and growing epoch lengths.
There is increasing interest in data-driven approaches for recommending optimal treatment strategies in many chronic disease management and critical care applications. Reinforcement learning methods are well-suited to this sequential decision-making problem, but must be trained and evaluated exclusively on retrospective medical record datasets as direct online exploration is unsafe and infeasible. Despite this requirement, the vast majority of treatment optimization studies use off-policy RL methods (e.g., Double Deep Q Networks (DDQN) or its variants) that are known to perform poorly in purely offline settings. Recent advances in offline RL, such as Conservative Q-Learning (CQL), offer a suitable alternative. But there remain challenges in adapting these approaches to real-world applications where suboptimal examples dominate the retrospective dataset and strict safety constraints need to be satisfied. In this work, we introduce a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training. We perform extensive experiments on two real-world tasks for diabetes and sepsis treatment optimization to compare performance of the proposed approach against prominent off-policy and offline RL baselines (DDQN and CQL). Across a range of principled and clinically relevant metrics, we show that our proposed approach enables substantial improvements in expected health outcomes and in accordance with relevant practice and safety guidelines.
Modeling difficulty, time-varying model, and uncertain external inputs are the main challenges for energy management of fuel cell hybrid electric vehicles. In the paper, a fuzzy reinforcement learning-based energy management strategy for fuel cell hybrid electric vehicles is proposed to reduce fuel consumption, maintain the batteries' long-term operation, and extend the lifetime of the fuel cells system. Fuzzy Q-learning is a model-free reinforcement learning that can learn itself by interacting with the environment, so there is no need for modeling the fuel cells system. In addition, frequent startup of the fuel cells will reduce the remaining useful life of the fuel cells system. The proposed method suppresses frequent fuel cells startup by considering the penalty for the times of fuel cell startups in the reward of reinforcement learning. Moreover, applying fuzzy logic to approximate the value function in Q-Learning can solve continuous state and action space problems. Finally, a python-based training and testing platform verify the effectiveness and self-learning improvement of the proposed method under conditions of initial state change, model change and driving condition change.
With the continuous increment of maritime applications, the development of marine networks for data offloading becomes necessary. However, the limited maritime network resources are very difficult to satisfy real-time demands. Besides, how to effectively handle multiple compute-intensive tasks becomes another intractable issue. Hence, in this paper, we focus on the decision of maritime task offloading by the cooperation of unmanned aerial vehicles (UAVs) and vessels. Specifically, we first propose a cooperative offloading framework, including the demands from marine Internet of Things (MIoTs) devices and resource providers from UAVs and vessels. Due to the limited energy and computation ability of UAVs, it is necessary to help better apply the vessels to computation offloading. Then, we formulate the studied problem into a Markov decision process, aiming to minimize the total execution time and energy cost. Then, we leverage Lyapunov optimization to convert the long-term constraints of the total execution time and energy cost into their short-term constraints, further yielding a set of per-time-slot optimization problems. Furthermore, we propose a Q-learning based approach to solve the short-term problem efficiently. Finally, simulation results are conducted to verify the correctness and effectiveness of the proposed algorithm.
Mobile edge computing (MEC) is a promising paradigm to meet the quality of service (QoS) requirements of latency-sensitive IoT applications. However, attackers may eavesdrop on the offloading decisions to infer the edge server's (ES's) queue information and users' usage patterns, thereby incurring the pattern privacy (PP) issue. Therefore, we propose an offloading strategy which jointly minimizes the latency, ES's energy consumption, and task dropping rate, while preserving PP. Firstly, we formulate the dynamic computation offloading procedure as a Markov decision process (MDP). Next, we develop a Differential Privacy Deep Q-learning based Offloading (DP-DQO) algorithm to solve this problem while addressing the PP issue by injecting noise into the generated offloading decisions. This is achieved by modifying the deep Q-network (DQN) with a Function-output Gaussian process mechanism. We provide a theoretical privacy guarantee and a utility guarantee (learning error bound) for the DP-DQO algorithm and finally, conduct simulations to evaluate the performance of our proposed algorithm by comparing it with greedy and DQN-based algorithms.
These days automation is being applied everywhere. In every environment, planning for the actions to be taken by the agents is an important aspect. In this paper, we plan to implement planning for multi-agents with a centralized controller. We compare three approaches: random policy, Q-learning, and Q-learning with Options Framework. We also show the effectiveness of planners by showing performance comparison between Q-Learning with Planner and without Planner.
The ongoing rise in cyberattacks and the lack of skilled professionals in the cybersecurity domain to combat these attacks show the need for automated tools capable of detecting an attack with good performance. Attackers disguise their actions and launch attacks that consist of multiple actions, which are difficult to detect. Therefore, improving defensive tools requires their calibration against a well-trained attacker. In this work, we propose a model of an attacking agent and environment and evaluate its performance using basic Q-Learning, Naive Q-learning, and DoubleQ-Learning, all of which are variants of Q-Learning. The attacking agent is trained with the goal of exfiltrating data whereby all the hosts in the network have a non-zero detection probability. Results show that the DoubleQ-Learning agent has the best overall performance rate by successfully achieving the goal in $70\%$ of the interactions.