Reinforcement Learning from human feedback (RLHF) has been shown a promising direction for aligning generative models with human intent and has also been explored in recent works for alignment of diffusion generative models. In this work, we provide a rigorous treatment by formulating the task of fine-tuning diffusion models, with reward functions learned from human feedback, as an exploratory continuous-time stochastic control problem. Our key idea lies in treating the score-matching functions as controls/actions, and upon this, we develop a unified framework from a continuous-time perspective, to employ reinforcement learning (RL) algorithms in terms of improving the generation quality of diffusion models. We also develop the corresponding continuous-time RL theory for policy optimization and regularization under assumptions of stochastic different equations driven environment. Experiments on the text-to-image (T2I) generation will be reported in the accompanied paper.
Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；Beijing University of Posts and Telecommunications（北京邮电大学）；Hangzhou Institute for Advanced Study at UCAS（UCAS杭州高等研究院）
Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning. Knowledge acquired during an unsupervised pre-training phase is often transferred by fine-tuning neural network weights once rewards are exposed, as is common practice in supervised domains. Given the nature of the reinforcement learning problem, we argue that standard fine-tuning strategies alone are not enough for efficient transfer in challenging domains. We introduce Behavior Transfer (BT), a technique that leverages pre-trained policies for ex…
Missouri University of Science and Technology（密苏里科技大学）
The real-time strategy game of StarCraft II has been posed as a challenge for reinforcement learning by Google's DeepMind. This study examines the use of an agent based on the Monte-Carlo Tree Search algorithm for optimizing the build order in StarCraft II, and discusses how its performance can be improved even further by combining it with a deep reinforcement learning neural network. The experimental results accomplished using Monte-Carlo Tree Search achieves a score similar to a novice human player by only using very limited time and computational resources, which paves the way to achieving …
Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；The Austrian Research Institute for Artificial Intelligence (OFAI)（奥地利人工智能研究所（OFAI））
Score following is the process of tracking a musical performance (audio) with respect to a known symbolic representation (a score). We start this paper by formulating score following as a multimodal Markov Decision Process, the mathematical foundation for sequential decision making. Given this formal definition, we address the score following task with state-of-the-art deep reinforcement learning (RL) algorithms such as synchronous advantage actor critic (A2C). In particular, we design multimodal RL agents that simultaneously learn to listen to music, read the scores from images of sheet music…
Future generations of mobile networks are expected to contain more and more antennas with growing complexity and more parameters. Optimizing these parameters is necessary for ensuring the good performance of the network. The scale of mobile networks makes it challenging to optimize antenna parameters using manual intervention or hand-engineered strategies. Reinforcement learning is a promising technique to address this challenge but existing methods often use local optimizations to scale to large network deployments. We propose a new multi-agent reinforcement learning algorithm to optimize mob…
Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
Nanjing University（南京大学）；Australia National University（澳大利亚国立大学）；Wuhan University（武汉大学）；National University of Singapore（新加坡国立大学）；University of Technology Sydney（技术科技大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Several AutoML approaches have been proposed to automate the machine learning (ML) process, such as searching for the ML model architectures and hyper-parameters. However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks. As ML systems are increasingly being used in a variety of mission-critical applications, improving the robustness of ML systems has become of utmost importance. In this paper, we propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL)--to per…
UC Santa Cruz（加州大学圣克鲁兹分校）；Northwestern University（西北大学）；Yale University（耶鲁大学）
We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded and known. SMRL uses score matching, an unnormalized density estimation technique that enables efficient estimation of the model parameter by ridge regression. Under standard regularity assumptions, SMRL achieves $\tilde O(d\sqrt{H^3T})$ online regret, where $H$ is the length of each episode and $T$ is the total number of interactions (ignoring polynomial depe…
Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often unnecessary. Deep Reinforcement Learning (DRL) offers a cost-effective alternative, where detectors are dynamically chosen based on the output of their predecessors, with their usefulness weighted against their computational cost. Despite their potential, DRL-based solutions are not widely used in this capacity, partly due to the difficulties in configuring the re…
Facebook AI Research（脸书人工智能研究院）；UC Berkeley（加州大学伯克利分校）
Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular…
Beijing National Laboratory for Condensed Matter Physics（北京凝聚态物理国家实验室）；School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100190, China（中国科学院大学物理科学学院）；Songshan Lake Materials Laboratory, Dongguan, Guangdong 523808, China（松山湖材料实验室）
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
University of California, Los Angeles, Los Angeles, CA, USA（加州大学洛杉矶分校）；Cognizant AI Lab, San Francisco, CA, USA（Cognizant AI实验室）；The University of Texas at Austin, Austin, TX, USA（德克萨斯大学奥斯汀分校）；Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院）
Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However, meta-reinforcement learning (meta-RL) algorithms have thus far been restricted to simple environments with narrow task distributions. Moreover, the paradigm of pretraining followed by fine-tuning to adapt to new tasks has emerged as a simple yet effective solution in supervised and self-supervised learning. This calls into question the benefits of meta-learning app…
Massachusetts Institute of Technology (MIT)（麻省理工学院）
We present a traffic simulation named DeepTraffic where the planning systems for a subset of the vehicles are handled by a neural network as part of a model-free, off-policy reinforcement learning process. The primary goal of DeepTraffic is to make the hands-on study of deep reinforcement learning accessible to thousands of students, educators, and researchers in order to inspire and fuel the exploration and evaluation of deep Q-learning network variants and hyperparameter configurations through large-scale, open competition. This paper investigates the crowd-sourced hyperparameter tuning of t…
Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has been reported to show meta-overfitting for certain tasks, especially for easy tasks where an agent can easily get high scores. To reduce effects of the meta-overfitting, we considered meta-RL with curriculum-based task sampling. Our method is Robust Meta Reinforcement Learning with Guided Task Sampling (RMRL-GTS), which is an effective method that restricts task sampling based on …
University of Oxford（牛津大学）；Facebook AI Research（脸书人工智能研究院）
Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal de…
Continuous direct yaw moment control systems such as torque-vectoring controller are an essential part for vehicle stabilization. This controller has been extensively researched with the central objective of maintaining the vehicle stability by providing consistent stable cornering response. The ability of careful tuning of the parameters in a torque-vectoring controller can significantly enhance vehicle's performance and stability. However, without any re-tuning of the parameters, especially in extreme driving conditions e.g. low friction surface or high velocity, the vehicle fails to maintai…
Fine tuning distributed systems is considered to be a craftsmanship, relying on intuition and experience. This becomes even more challenging when the systems need to react in near real time, as streaming engines have to do to maintain pre-agreed service quality metrics. In this article, we present an automated approach that builds on a combination of supervised and reinforcement learning methods to recommend the most appropriate lever configurations based on previous load. With this, streaming engines can be automatically tuned without requiring a human to determine the right way and proper ti…
Reinforcement learning (RL) has had many successes in both "deep" and "shallow" settings. In both cases, significant hyperparameter tuning is often required to achieve good performance. Furthermore, when nonlinear function approximation is used, non-stationarity in the state representation can lead to learning instability. A variety of techniques exist to combat this --- most notably large experience replay buffers or the use of multiple parallel actors. These techniques come at the cost of moving away from the online RL problem as it is traditionally formulated (i.e., a single agent learning …
Technische Universität Berlin（柏林工业大学）；University of Glasgow（格拉斯哥大学）；HPI, University of Potsdam（波茨坦大学哈索·普拉特纳研究所）
Distributed file systems are widely used nowadays, yet using their default configurations is often not optimal. At the same time, tuning configuration parameters is typically challenging and time-consuming. It demands expertise and tuning operations can also be expensive. This is especially the case for static parameters, where changes take effect only after a restart of the system or workloads. We propose a novel approach, Magpie, which utilizes deep reinforcement learning to tune static parameters by strategically exploring and exploiting configuration parameter spaces. To boost the tuning o…
Reinforcement learning is one of the most popular approaches for automated game playing. This method allows an agent to estimate the expected utility of its state in order to make optimal actions in an unknown environment. We seek to apply reinforcement learning algorithms to the game Flappy Bird. We implement SARSA and Q-Learning with some modifications such as $ε$-greedy policy, discretization and backward updates. We find that SARSA and Q-Learning outperform the baseline, regularly achieving scores of 1400+, with the highest in-game score of 2069.
Choosing an appropriate parameter set for the designed controller is critical for the final performance but usually requires a tedious and careful tuning process, which implies a strong need for automatic tuning methods. However, among existing methods, derivative-free ones suffer from poor scalability or low efficiency, while gradient-based ones are often unavailable due to possibly non-differentiable controller structure. To resolve the issues, we tackle the controller tuning problem using a novel derivative-free reinforcement learning (RL) framework, which performs timestep-wise perturbatio…
Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, but typically require a very large number of samples to achieve good performance. Model-based algorithms, in principle, can provide for much more efficient learning, but have proven difficult to extend to expressive, high-capacity models such as deep neural networks. In this work, we demonstrate that medium-sized neural network models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning …
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）
