In this paper, we present a reinforcement learning (RL) method for solving optimal false data injection attack problems in probabilistic Boolean control networks (PBCNs) where the attacker lacks knowledge of the system model. Specifically, we employ a Q-learning (QL) algorithm to address this problem. We then propose an improved QL algorithm that not only enhances learning efficiency but also obtains optimal attack strategies for large-scale PBCNs that the standard QL algorithm cannot handle. Finally, we verify the effectiveness of our proposed approach by considering two attacked PBCNs, including a 10-node network and a 28-node network.
The reinforcement learning algorithms have often been applied to social robots. However, most reinforcement learning algorithms were not optimized for the use of social robots, and consequently they may bore users. We proposed a new reinforcement learning method specialized for the social robot, the FRAC-Q-learning, that can avoid user boredom. The proposed algorithm consists of a forgetting process in addition to randomizing and categorizing processes. This study evaluated interest and boredom hardness scores of the FRAC-Q-learning by a comparison with the traditional Q-learning. The FRAC-Q-learning showed significantly higher trend of interest score, and indicated significantly harder to bore users compared to the traditional Q-learning. Therefore, the FRAC-Q-learning can contribute to develop a social robot that will not bore users. The proposed algorithm has a potential to apply for Web-based communication and educational systems. This paper presents the entire process, detailed implementation and a detailed evaluation method of the of the FRAC-Q-learning for the first time.
The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with general function approximation. Our key algorithmic design includes (1) a general deterministic policy-switching strategy that achieves low switching cost, (2) a monotonic value function structure with carefully controlled function class complexity, and (3) a variance-weighted regression scheme that exploits historical trajectories with high data efficiency. MQL-UCB achieves minimax optimal regret of $\tilde{O}(d\sqrt{HK})$ when $K$ is sufficiently large and near-optimal policy switching cost of $\tilde{O}(dH)$, with $d$ being the eluder dimension of the function class, $H$ being the planning horizon, and $K$ being the number of episodes. Our work sheds light on designing provably sample-efficient and deployment-efficient Q-learning with nonlinear function approximation.
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline setting. The main approach to correct this shift has been through importance sampling, which leads to high-variance gradients. Other approaches, such as conservatism or behavior-regularization, regularize the policy at the cost of performance. In this paper, we propose a new approach for stable off-policy Q-Learning. Our method, Projected Off-Policy Q-Learning (POP-QL), is a novel actor-critic algorithm that simultaneously reweights off-policy samples and constrains the policy to prevent divergence and reduce value-approximation error. In our experiments, POP-QL not only shows competitive performance on standard benchmarks, but also out-performs competing methods in tasks where the data-collection policy is significantly sub-optimal.
Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle uncertainty due to potential information loss. In this paper, we consider a cooperative multi-agent system where the agents act and exchange information in a decentralized manner using a limited and unreliable channel. To cope with such channel constraints, we propose a novel communication approach based on independent Q-learning. Our method allows agents to dynamically adapt how much information to share by sending messages of different sizes, depending on their local observations and the channel's properties. In addition to this message size selection, agents learn to encode and decode messages to improve their jointly trained policies. We show that our approach outperforms approaches without adaptive capabilities in a novel cooperative digit-prediction environment and discuss its limitations in the traffic junction environment.
Large vision-language models are steadily gaining personalization capabilities at the cost of fine-tuning or data augmentation. We present two models for image generation using model-agnostic learning that align semantic priors with generative capabilities. RLDF, or Reinforcement Learning from Diffusion Feedback, is a singular approach for visual imitation through prior-preserving reward function guidance. This employs Q-learning (with standard Q*) for generation and follows a semantic-rewarded trajectory for image search through finite encoding-tailored actions. The second proposed method, noisy diffusion gradient, is optimization driven. At the root of both methods is a special CFG encoding that we propose for continual semantic guidance. Using only a single input image and no text input, RLDF generates high-quality images over varied domains including retail, sports and agriculture showcasing class-consistency and strong visual diversity. Project website is available at https://infernolia.github.io/RLDF.
This paper studies an infinite horizon optimal tracking portfolio problem using capital injection in incomplete market models. The benchmark process is modelled by a geometric Brownian motion with zero drift driven by some unhedgeable risk. The relaxed tracking formulation is adopted where the fund account compensated by the injected capital needs to outperform the benchmark process at any time, and the goal is to minimize the cost of the discounted total capital injection. When model parameters are known, we formulate the equivalent auxiliary control problem with reflected state dynamics, for which the classical solution of the HJB equation with Neumann boundary condition is obtained explicitly. When model parameters are unknown, we introduce the exploratory formulation for the auxiliary control problem with entropy regularization and develop the continuous-time q-learning algorithm in models of reflected diffusion processes. In some illustrative numerical example, we show the satisfactory performance of the q-learning algorithm.
Oberman gave a stochastic control formulation of the problem of estimating the convex envelope of a non-convex function. Based on this, we develop a reinforcement learning scheme to approximate the convex envelope, using a variant of Q-learning for controlled optimal stopping. It shows very promising results on a standard library of test problems.
In this paper, a machine learning-based decentralized time division multiple access (TDMA) algorithm for visible light communication (VLC) Internet of Things (IoT) networks is proposed. The proposed algorithm is based on Q-learning, a reinforcement learning algorithm. This paper considers a decentralized condition in which there is no coordinator node for sending synchronization frames and assigning transmission time slots to other nodes. The proposed algorithm uses a decentralized manner for synchronization, and each node uses the Q-learning algorithm to find the optimal transmission time slot for sending data without collisions. The proposed algorithm is implemented on a VLC hardware system, which had been designed and implemented in our laboratory. Average reward, convergence time, goodput, average delay, and data packet size are evaluated parameters. The results show that the proposed algorithm converges quickly and provides collision-free decentralized TDMA for the network. The proposed algorithm is compared with carrier-sense multiple access with collision avoidance (CSMA/CA) algorithm as a potential selection for decentralized VLC IoT networks. The results show that the proposed algorithm provides up to 61% more goodput and up to 49% less average delay than CSMA/CA.
In advancing the understanding of natural decision-making processes, inverse reinforcement learning (IRL) methods have proven instrumental in reconstructing animal's intentions underlying complex behaviors. Given the recent development of a continuous-time multi-intention IRL framework, there has been persistent inquiry into inferring discrete time-varying rewards with IRL. To address this challenge, we introduce the class of hierarchical inverse Q-learning (HIQL) algorithms. Through an unsupervised learning process, HIQL divides expert trajectories into multiple intention segments, and solves the IRL problem independently for each. Applying HIQL to simulated experiments and several real animal behavior datasets, our approach outperforms current benchmarks in behavior prediction and produces interpretable reward functions. Our results suggest that the intention transition dynamics underlying complex decision-making behavior is better modeled by a step function instead of a smoothly varying function. This advancement holds promise for neuroscience and cognitive science, contributing to a deeper understanding of decision-making and uncovering underlying brain mechanisms.
Deep reinforcement learning suffers from catastrophic forgetting and sample inefficiency making it less applicable to the ever-changing real world. However, the ability to use previously learned knowledge is essential for AI agents to quickly adapt to novelties. Often, certain spatial information observed by the agent in the previous interactions can be leveraged to infer task-specific rules. Inferred rules can then help the agent to avoid potentially dangerous situations in the previously unseen states and guide the learning process increasing agent's novelty adaptation speed. In this work, we propose a general framework that is applicable to deep reinforcement learning agents. Our framework provides the agent with an autonomous way to discover the task-specific rules in the novel environments and self-supervise it's learning. We provide a rule-driven deep Q-learning agent (RDQ) as one possible implementation of that framework. We show that RDQ successfully extracts task-specific rules as it interacts with the world and uses them to drastically increase its learning efficiency. In our experiments, we show that the RDQ agent is significantly more resilient to the novelties than the baseline agents, and is able to detect and adapt to novel situations faster.
In this paper, we propose a reinforcement learning algorithm to solve a multi-agent Markov decision process (MMDP). The goal, inspired by Blackwell's Approachability Theorem, is to lower the time average cost of each agent to below a pre-specified agent-specific bound. For the MMDP, we assume the state dynamics to be controlled by the joint actions of agents, but the per-stage costs to only depend on the individual agent's actions. We combine the Q-learning algorithm for a weighted combination of the costs of each agent, obtained by a gossip algorithm with the Metropolis-Hastings or Multiplicative Weights formalisms to modulate the averaging matrix of the gossip. We use multiple timescales in our algorithm and prove that under mild conditions, it approximately achieves the desired bounds for each of the agents. We also demonstrate the empirical performance of this algorithm in the more general setting of MMDPs having jointly controlled per-stage costs.
The realm of High-Frequency Trading (HFT) is characterized by rapid decision-making processes that capitalize on fleeting market inefficiencies. As the financial markets become increasingly competitive, there is a pressing need for innovative strategies that can adapt and evolve with changing market dynamics. Enter Reinforcement Learning (RL), a branch of machine learning where agents learn by interacting with their environment, making it an intriguing candidate for HFT applications. This paper dives deep into the integration of RL in statistical arbitrage strategies tailored for HFT scenarios. By leveraging the adaptive learning capabilities of RL, we explore its potential to unearth patterns and devise trading strategies that traditional methods might overlook. We delve into the intricate exploration-exploitation trade-offs inherent in RL and how they manifest in the volatile world of HFT. Furthermore, we confront the challenges of applying RL in non-stationary environments, typical of financial markets, and investigate methodologies to mitigate associated risks. Through extensive simulations and backtests, our research reveals that RL not only enhances the adaptability of trading strategies but also shows promise in improving profitability metrics and risk-adjusted returns. This paper, therefore, positions RL as a pivotal tool for the next generation of HFT-based statistical arbitrage, offering insights for both researchers and practitioners in the field.
The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first investigate the use of \emph{offline} RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms, including behavior constrained Q-learning (BCQ), conservative Q-learning (CQL), and implicit Q-learning (IQL), for a specific RRM problem that aims at maximizing a linear combination {of sum and} 5-percentile rates via user scheduling. We observe that the performance of offline RL for the RRM problem depends critically on the behavior policy used for data collection, and further propose a novel offline RL solution that leverages heterogeneous datasets collected by different behavior policies. We show that with a proper mixture of the datasets, offline RL can produce a near-optimal RL policy even when all involved behavior policies are highly suboptimal.
This study enhances a Deep Q-Network (DQN) trading model by incorporating advanced techniques like Prioritized Experience Replay, Regularized Q-Learning, Noisy Networks, Dueling, and Double DQN. Extensive tests on assets like BTC/USD and AAPL demonstrate superior performance compared to the original model, with marked increases in returns and Sharpe Ratio, indicating improved risk-adjusted rewards. Notably, convolutional neural network (CNN) architectures, both 1D and 2D, significantly boost returns, suggesting their effectiveness in market trend analysis. Across instruments, these enhancements have yielded stable and high gains, eclipsing the baseline and highlighting the potential of CNNs in trading systems. The study suggests that applying sophisticated deep learning within reinforcement learning can greatly enhance automated trading, urging further exploration into advanced methods for broader financial applicability. The findings advocate for the continued evolution of AI in finance.
This paper introduces a reinforcement learning (RL) approach to address the challenges associated with configuring and optimizing genetic algorithms (GAs) for solving difficult combinatorial or non-linear problems. The proposed RL+GA method was specifically tested on the flow shop scheduling problem (FSP). The hybrid algorithm incorporates neural networks (NN) and uses the off-policy method Q-learning or the on-policy method Sarsa(0) to control two key genetic algorithm (GA) operators: parent selection mechanism and mutation. At each generation, the RL agent's action is determining the selection method, the probability of the parent selection and the probability of the offspring mutation. This allows the RL agent to dynamically adjust the selection and mutation based on its learned policy. The results of the study highlight the effectiveness of the RL+GA approach in improving the performance of the primitive GA. They also demonstrate its ability to learn and adapt from population diversity and solution improvements over time. This adaptability leads to improved scheduling solutions compared to static parameter configurations while maintaining population diversity throughout the evolutionary process.
We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) to enhance the optimality of attention-based sequence generation, focusing on long-term outcomes. This integration proves particularly effective in solving combinatorial optimization (CO) tasks, especially the Travelling Salesman Problem (TSP), which is the focus of our study. We address this challenge by defining a Markov Decision Process (MDP) compatible with PQN, which involves iterative graph embedding, encoding and decoding by an LSTM-based recurrent neural network. This process generates a context vector and computes raw attention scores, which are dynamically adjusted by Q-values calculated for all available state-action pairs before applying softmax. The resulting attention vector is utilized as an action distribution, with actions selected hinged to exploration-exploitation dynamic adaptibility of PQN. Our empirical results demonstrate the efficacy of this approach, also testing the model in unstable environments.
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents. No methods have been proposed for addressing RO in multi-agent policy gradient (MAPG) methods although these methods produce state-of-the-art results. To address this gap, we propose a general, yet simple, framework to enable optimistic updates in MAPG methods that alleviate the RO problem. Our approach involves clipping the advantage to eliminate negative values, thereby facilitating optimistic updates in MAPG. The optimism prevents individual agents from quickly converging to a local optimum. Additionally, we provide a formal analysis to show that the proposed method retains optimality at a fixed point. In extensive evaluations on a diverse set of tasks including the *Multi-agent MuJoCo* and *Overcooked* benchmarks, our method outperforms strong baselines on 13 out of 19 tested tasks and matches the performance on the rest.
As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergence involve an ergodicity and a positivity criterion. We provide a precise characterization on the limit of the iterates and conditions on the environment and initializations for convergence. As our second contribution, we discuss the implications and applications of this theorem to a variety of stochastic control problems with non-Markovian environments involving (i) quantized approximations of fully observed Markov Decision Processes (MDPs) with continuous spaces (where quantization break down the Markovian structure), (ii) quantized approximations of belief-MDP reduced partially observable MDPS (POMDPs) with weak Feller continuity and a mild version of filter stability (which requires the knowledge of the model by the controller), (iii) finite window approximations of POMDPs under a uniform controlled filter stability (which does not require the knowledge of the model), and (iv) for multi-agent models where convergence of learning dynamics to a new class of equilibria, subjective Q-learning equilibria, will be studied. In addition to the convergence theorem, some implications of the theorem above are new to the literature and others are interpreted as applications of the convergence theorem. Some open problems are noted.
Deep learning is emerging as an effective tool in drug discovery, with potential applications in both predictive and generative models. Generative Flow Networks (GFlowNets/GFNs) are a recently introduced method recognized for the ability to generate diverse candidates, in particular in small molecule generation tasks. In this work, we introduce double GFlowNets (DGFNs). Drawing inspiration from reinforcement learning and Double Deep Q-Learning, we introduce a target network used to sample trajectories, while updating the main network with these sampled trajectories. Empirical results confirm that DGFNs effectively enhance exploration in sparse reward domains and high-dimensional state spaces, both challenging aspects of de-novo design in drug discovery.