Multi-agent reinforcement learning (MARL) tasks often utilize a centralized training with decentralized execution (CTDE) framework. QMIX is a successful CTDE method that learns a credit assignment function to derive local value functions from a global value function, defining a deterministic local policy. However, QMIX is hindered by its poor exploration strategy. While maximum entropy reinforcement learning (RL) promotes better exploration through stochastic policies, QMIX's process of credit assignment conflicts with the maximum entropy objective and the decentralized execution requirement, making it unsuitable for maximum entropy RL. In this paper, we propose an enhancement to QMIX by incorporating an additional local Q-value learning method within the maximum entropy RL framework. Our approach constrains the local Q-value estimates to maintain the correct ordering of all actions. Due to the monotonicity of the QMIX value function, these updates ensure that locally optimal actions align with globally optimal actions. We theoretically prove the monotonic improvement and convergence of our method to an optimal solution. Experimentally, we validate our algorithm in matrix games, Multi-Agent Particle Environment and demonstrate state-of-the-art performance in SMAC-v2.
High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, \emph{e.g.,} hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, \emph{a.k.a.} MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making. Extensive experiments on various cryptocurrency markets demonstrate that MacroHFT can achieve state-of-the-art performance on minute-level trading tasks.
Dental disease is still one of the most common chronic diseases in the United States. While dental disease is preventable through healthy oral self-care behaviors (OSCB), this basic behavior is not consistently practiced. We have developed Oralytics, an online, reinforcement learning (RL) algorithm that optimizes the delivery of personalized intervention prompts to improve OSCB. In this paper, we offer a full overview of algorithm design decisions made using prior data, domain expertise, and experiments in a simulation test bed. The finalized RL algorithm was deployed in the Oralytics clinical trial, conducted from fall 2023 to summer 2024.
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization (PPO) has led to new line work on Direct Policy Optimization (DPO), which treats RLHF in a supervised learning framework. The increased practical use of these RLHF methods warrants an analysis of their vulnerabilities. In this work, we investigate the vulnerabilities of DPO to poisoning attacks under different scenarios and compare the effectiveness of preference poisoning, a first of its kind. We comprehensively analyze DPO's vulnerabilities under different types of attacks, i.e., backdoor and non-backdoor attacks, and different poisoning methods across a wide array of language models, i.e., LLama 7B, Mistral 7B, and Gemma 7B. We find that unlike PPO-based methods, which, when it comes to backdoor attacks, require at least 4\% of the data to be poisoned to elicit harmful behavior, we exploit the true vulnerabilities of DPO more simply so we can poison the model with only as much as 0.5\% of the data. We further investigate the potential reasons behind the vulnerability and how well this vulnerability translates into backdoor vs non-backdoor attacks.
Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential of such specialized training environments is still vastly underexplored, despite their capacity to dramatically speed up training. The framework of synthetic environments takes a first step in this direction by meta-learning neural network-based Markov decision processes (MDPs). The initial approach was limited to toy problems and produced environments that did not transfer to unseen RL algorithms. We extend this approach in three ways: Firstly, we modify the meta-learning algorithm to discover environments invariant towards hyperparameter configurations and learning algorithms. Secondly, by leveraging hardware parallelism and introducing a curriculum on an agent's evaluation episode horizon, we can achieve competitive results on several challenging continuous control problems. Thirdly, we surprisingly find that contextual bandits enable training RL agents that transfer well to their evaluation environment, even if it is a complex MDP. Hence, we set up our experiments to train synthetic contextual bandits, which perform on par with synthetic MDPs, yield additional insights into the evaluation environment, and can speed up downstream applications.
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging approximate sampling-based exploration schemes are promising, most existing algorithms are specific to linear Markov Decision Processes (MDP) with suboptimal regret bounds, or only use the most basic samplers such as Langevin Monte Carlo. In this work, we propose an algorithmic framework that incorporates different approximate sampling methods with the recently proposed Feel-Good Thompson Sampling (FGTS) approach (Zhang, 2022; Dann et al., 2021), which was previously known to be computationally intractable in general. When applied to linear MDPs, our regret analysis yields the best known dependency of regret on dimensionality, surpassing existing randomized algorithms. Additionally, we provide explicit sampling complexity for each employed sampler. Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines. On several challenging games from the Atari 57 suite, our algorithms achieve performance that is either better than or on par with other strong baselines from the deep RL literature.
Unmanned Combat Aerial Vehicle (UCAV) dogfight, which refers to a fight between two or more UCAVs usually at close quarters, plays a decisive role on the aerial battlefields. With the evolution of artificial intelligence, dogfight progressively transits towards intelligent and autonomous modes. However, the development of autonomous dogfight policy learning is hindered by challenges such as weak exploration capabilities, low learning efficiency, and unrealistic simulated environments. To overcome these challenges, this paper proposes a novel imitative reinforcement learning framework, which efficiently leverages expert data while enabling autonomous exploration. The proposed framework not only enhances learning efficiency through expert imitation, but also ensures adaptability to dynamic environments via autonomous exploration with reinforcement learning. Therefore, the proposed framework can learn a successful dogfight policy of 'pursuit-lock-launch' for UCAVs. To support data-driven learning, we establish a dogfight environment based on the Harfang3D sandbox, where we conduct extensive experiments. The results indicate that the proposed framework excels in multistage dogfight, significantly outperforms state-of-the-art reinforcement learning and imitation learning methods. Thanks to the ability of imitating experts and autonomous exploration, our framework can quickly learn the critical knowledge in complex aerial combat tasks, achieving up to a 100% success rate and demonstrating excellent robustness.
The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage is both tedious and challenging, and often fails to include scenarios that LLMs need to improve on the most. In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. The adversarial agent's task at each step is to generate prompts that expose the weakness of the defensive agent. In return, the defensive agent seeks to improve its responses to these newly identified prompts it struggled with, based on feedback from the reward model. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experimental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents.
Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an auxiliary pessimistic model, updated adversarially, to estimate the worst-case MDP within a Kullback-Leibler uncertainty set. In comparison to several existing works, our work does not impose any additional conditions on the training environment, such as the need for a parametric simulator. To test the effectiveness of the proposed pessimistic model in enhancing policy robustness, we integrate it into a practical RL algorithm, called Robust Model-Based Policy Optimization (RMBPO). Our experimental results indicate a notable improvement in policy robustness on high-dimensional MuJoCo control tasks, with the auxiliary model enhancing the performance of the learned policy in distorted MDPs. We further explore the learned deviation between the proposed auxiliary world model and the nominal model, to examine how pessimism is achieved. By learning a pessimistic world model and demonstrating its role in improving policy robustness, our research contributes towards making (model-based) RL more robust.
In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk of the latter while solving the two tasks in parallel. Unlike previous work, we do not assume the low-tier and high-tier tasks share the same dynamics or reward functions, and focus on robust knowledge transfer without prior knowledge on the task similarity. We identify a natural and necessary condition called the ``Optimal Value Dominance'' for our objective. Under this condition, we propose novel online learning algorithms such that, for the high-tier task, it can achieve constant regret on partial states depending on the task similarity and retain near-optimal regret when the two tasks are dissimilar, while for the low-tier task, it can keep near-optimal without making sacrifice. Moreover, we further study the setting with multiple low-tier tasks, and propose a novel transfer source selection mechanism, which can ensemble the information from all low-tier tasks and allow provable benefits on a much larger state-action space.
Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two types of uncertainty sets for training and evaluation. Our benchmark aims to standardize robust reinforcement learning tasks, facilitating reproducible and comparable experiments, in particular those from recent state-of-the-art contributions, for which we demonstrate the use of RRLS. It is also designed to be easily expandable to new environments. The source code is available at \href{https://github.com/SuReLI/RRLS}{https://github.com/SuReLI/RRLS}.
In swarm robotics, confrontation including the pursuit-evasion game is a key scenario. High uncertainty caused by unknown opponents' strategies, dynamic obstacles, and insufficient training complicates the action space into a hybrid decision process. Although the deep reinforcement learning method is significant for swarm confrontation since it can handle various sizes, as an end-to-end implementation, it cannot deal with the hybrid process. Here, we propose a novel hierarchical reinforcement learning approach consisting of a target allocation layer, a path planning layer, and the underlying dynamic interaction mechanism between the two layers, which indicates the quantified uncertainty. It decouples the hybrid process into discrete allocation and continuous planning layers, with a probabilistic ensemble model to quantify the uncertainty and regulate the interaction frequency adaptively. Furthermore, to overcome the unstable training process introduced by the two layers, we design an integration training method including pre-training and cross-training, which enhances the training efficiency and stability. Experiment results in both comparison, ablation, and real-robot studies validate the effectiveness and generalization performance of our proposed approach. In our defined experiments with twenty to forty agents, the win rate of the proposed method reaches around ninety percent, outperforming other traditional methods.
In this paper, we consider multi-objective reinforcement learning, which arises in many real-world problems with multiple optimization goals. We approach the problem with a max-min framework focusing on fairness among the multiple goals and develop a relevant theory and a practical model-free algorithm under the max-min framework. The developed theory provides a theoretical advance in multi-objective reinforcement learning, and the proposed algorithm demonstrates a notable performance improvement over existing baseline methods.
This paper presents Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF), a novel approach to improving the alignment and performance of language models trained using reinforcement learning from AI feedback (RLAIF). In contrast to standard approaches that train a single preference model to represent all human preferences, MORLAIF decomposes this task into multiple simpler principles, such as toxicity, factuality, and sycophancy. Separate preference models are trained for each principle using feedback from GPT-3.5-Turbo. These preference model scores are then combined using different scalarization functions to provide a reward signal for Proximal Policy Optimization (PPO) training of the target language model. Our experiments indicate that MORLAIF outperforms the standard RLAIF baselines and that MORLAIF can be used to align larger language models using smaller ones. Surprisingly, the choice of scalarization function does not appear to significantly impact the results.
This work aims to investigate semantic communication in high-speed mobile Internet of vehicles (IoV) environments, with a focus on the spectrum sharing between vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. We specifically address spectrum scarcity and network traffic and then propose a semantic-aware spectrum sharing algorithm (SSS) based on the deep reinforcement learning (DRL) soft actor-critic (SAC) approach. Firstly, we delve into the extraction of semantic information. Secondly, we redefine metrics for semantic information in V2V and V2I spectrum sharing in IoV environments, introducing high-speed semantic spectrum efficiency (HSSE) and semantic transmission rate (HSR). Finally, we employ the SAC algorithm for decision optimization in V2V and V2I spectrum sharing based on semantic information. This optimization encompasses the optimal link of V2V and V2I sharing strategies, the transmission power for vehicles sending semantic information and the length of transmitted semantic symbols, aiming at maximizing HSSE of V2I and enhancing success rate of effective semantic information transmission (SRS) of V2V. Experimental results demonstrate that the SSS algorithm outperforms other baseline algorithms, including other traditional-communication-based spectrum sharing algorithms and spectrum sharing algorithm using other reinforcement learning approaches. The SSS algorithm exhibits a 15% increase in HSSE and approximately a 7% increase in SRS.
Adaptive brain stimulation can treat neurological conditions such as Parkinson's disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient heterogeneity, each patient requires a unique stimulation policy to achieve optimal neural responses. Model-free reinforcement learning (MFRL) holds promise in learning effective policies for a variety of similar control tasks, but is limited in domains like brain stimulation by a need for numerous costly environment interactions. In this work we introduce Coprocessor Actor Critic, a novel, model-based reinforcement learning (MBRL) approach for learning neural coprocessor policies for brain stimulation. Our key insight is that coprocessor policy learning is a combination of learning how to act optimally in the world and learning how to induce optimal actions in the world through stimulation of an injured brain. We show that our approach overcomes the limitations of traditional MFRL methods in terms of sample efficiency and task success and outperforms baseline MBRL approaches in a neurologically realistic model of an injured brain.
In this research, we introduce a deep reinforcement learning-based control approach to address the intricate challenge of the robotic pre-grasping phase under microgravity conditions. Leveraging reinforcement learning eliminates the necessity for manual feature design, therefore simplifying the problem and empowering the robot to learn pre-grasping policies through trial and error. Our methodology incorporates an off-policy reinforcement learning framework, employing the soft actor-critic technique to enable the gripper to proficiently approach a free-floating moving object, ensuring optimal pre-grasp success. For effective learning of the pre-grasping approach task, we developed a reward function that offers the agent clear and insightful feedback. Our case study examines a pre-grasping task where a Robotiq 3F gripper is required to navigate towards a free-floating moving target, pursue it, and subsequently position itself at the desired pre-grasp location. We assessed our approach through a series of experiments in both simulated and real-world environments. The source code, along with recordings of real-world robot grasping, is available at Fanuc_Robotiq_Grasp.
In this paper, we introduce Multi-Objective Deep Centralized Multi-Agent Actor-Critic (MO- DCMAC), a multi-objective reinforcement learning (MORL) method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is non-linear. We evaluated MO-DCMAC using two utility functions, which use probability of collapse and cost as input. The first utility function is the Threshold utility, in which MO-DCMAC should minimize cost so that the probability of collapse is never above the threshold. The second is based on the Failure Mode, Effects, and Criticality Analysis (FMECA) methodology used by asset managers to asses maintenance plans. We evaluated MO-DCMAC, with both utility functions, in multiple maintenance environments, including ones based on a case study of the historical quay walls of Amsterdam. The performance of MO-DCMAC was compared against multiple rule-based policies based on heuristics currently used for constructing maintenance plans. Our results demonstrate that MO-DCMAC outperforms traditional rule-based policies across various environments and utility functions.
The expected regret of any reinforcement learning algorithm is lower bounded by $\Omega\left(\sqrt{DXAT}\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing systems often have a diameter that is exponential in the buffer size $S$, making the previous lower bound prohibitive for any practical use. We propose an algorithm inspired by UCRL2, and use the structure of the problem to upper bound the expected total regret by $O(S\log T + \sqrt{mT \log T})$ in the finite server case. In the infinite server case, we prove that the dependence of the regret on $S$ disappears.
In offline reinforcement learning, in-sample learning methods have been widely used to prevent performance degradation caused by evaluating out-of-distribution actions from the dataset. Extreme Q-learning (XQL) employs a loss function based on the assumption that Bellman error follows a Gumbel distribution, enabling it to model the soft optimal value function in an in-sample manner. It has demonstrated strong performance in both offline and online reinforcement learning settings. However, issues remain, such as the instability caused by the exponential term in the loss function and the risk of the error distribution deviating from the Gumbel distribution. Therefore, we propose Maclaurin Expanded Extreme Q-learning to enhance stability. In this method, applying Maclaurin expansion to the loss function in XQL enhances stability against large errors. This approach involves adjusting the modeled value function between the value function under the behavior policy and the soft optimal value function, thus achieving a trade-off between stability and optimality depending on the order of expansion. It also enables adjustment of the error distribution assumption from a normal distribution to a Gumbel distribution. Our method significantly stabilizes learning in online RL tasks from DM Control, where XQL was previously unstable. Additionally, it improves performance in several offline RL tasks from D4RL.