PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2212.07489공식 코드 · Papers with Code

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-Agent Challenge (SMAC) has become a popular testbed for centralised training with decentralised execution. However, after years of sustained improvement on SMAC, algorithms now achieve near-perfect performance. In this work, we conduct new analysis demonstrating that SMAC lacks the stochasticity and partial observability to require complex *closed-loop* policies. In particular, we show that an *open-loop* policy conditioned only on the timestep can achieve non-trivial win rates for many SMAC scenarios. To address this limitation, we introduce SMACv2, a new version of the benchmark where scenarios are procedurally generated and require agents to generalise to previously unseen settings (from the same distribution) during evaluation. We also introduce the extended partial observability challenge (EPO), which augments SMACv2 to ensure meaningful partial observability. We show that these changes ensure the benchmark requires the use of *closed-loop* policies. We evaluate state-of-the-art algorithms on SMACv2 and show that it presents significant challenges not present in the original benchmark. Our analysis illustrates that SMACv2 addresses the discovered deficiencies of SMAC and can help benchmark the next generation of MARL methods. Videos of training are available at https://sites.google.com/view/smacv2.

arXiv:2401.06604

Identifying Policy Gradient Subspaces

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised learning can be accelerated by leveraging the fact that gradients lie in a low-dimensional and slowly-changing subspace. In this paper, we conduct a thorough evaluation of this phenomenon for two popular deep policy gradient methods on various simulated benchmark tasks. Our results demonstrate the existence of such gradient subspaces despite the continuously changing data distribution inherent to reinforcement learning. These findings reveal promising directions for future work on more efficient reinforcement learning, e.g., through improving parameter-space exploration or enabling second-order optimization.

arXiv:2401.06566

Maximum Causal Entropy Inverse Reinforcement Learning for Mean-Field Games

In this paper, we introduce the maximum casual entropy Inverse Reinforcement Learning (IRL) problem for discrete-time mean-field games (MFGs) under an infinite-horizon discounted-reward optimality criterion. The state space of a typical agent is finite. Our approach begins with a comprehensive review of the maximum entropy IRL problem concerning deterministic and stochastic Markov decision processes (MDPs) in both finite and infinite-horizon scenarios. Subsequently, we formulate the maximum casual entropy IRL problem for MFGs - a non-convex optimization problem with respect to policies. Leveraging the linear programming formulation of MDPs, we restructure this IRL problem into a convex optimization problem and establish a gradient descent algorithm to compute the optimal solution with a rate of convergence. Finally, we present a new algorithm by formulating the MFG problem as a generalized Nash equilibrium problem (GNEP), which is capable of computing the mean-field equilibrium (MFE) for the forward RL problem. This method is employed to produce data for a numerical example. We note that this novel algorithm is also applicable to general MFE computations.

arXiv:2401.06514공식 코드 · Papers with Code

Personalized Reinforcement Learning with a Budget of Policies

Personalization in machine learning (ML) tailors models' decisions to the individual characteristics of users. While this approach has seen success in areas like recommender systems, its expansion into high-stakes fields such as healthcare and autonomous driving is hindered by the extensive regulatory approval processes involved. To address this challenge, we propose a novel framework termed represented Markov Decision Processes (r-MDPs) that is designed to balance the need for personalization with the regulatory constraints. In an r-MDP, we cater to a diverse user population, each with unique preferences, through interaction with a small set of representative policies. Our objective is twofold: efficiently match each user to an appropriate representative policy and simultaneously optimize these policies to maximize overall social welfare. We develop two deep reinforcement learning algorithms that efficiently solve r-MDPs. These algorithms draw inspiration from the principles of classic K-means clustering and are underpinned by robust theoretical foundations. Our empirical investigations, conducted across a variety of simulated environments, showcase the algorithms' ability to facilitate meaningful personalization even under constrained policy budgets. Furthermore, they demonstrate scalability, efficiently adapting to larger policy budgets.

arXiv:2401.05341

Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design

The field of antibody-based therapeutics has grown significantly in recent years, with targeted antibodies emerging as a potentially effective approach to personalized therapies. Such therapies could be particularly beneficial for complex, highly individual diseases such as cancer. However, progress in this field is often constrained by the extensive search space of amino acid sequences that form the foundation of antibody design. In this study, we introduce a novel reinforcement learning method specifically tailored to address the unique challenges of this domain. We demonstrate that our method can learn the design of high-affinity antibodies against multiple targets in silico, utilizing either online interaction or offline datasets. To the best of our knowledge, our approach is the first of its kind and outperforms existing methods on all tested antigens in the Absolut! database.

arXiv:2401.05710공식 코드 · Papers with Code

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards

The reward signal plays a central role in defining the desired behaviors of agents in reinforcement learning (RL). Rewards collected from realistic environments could be perturbed, corrupted, or noisy due to an adversary, sensor error, or because they come from subjective human feedback. Thus, it is important to construct agents that can learn under such rewards. Existing methodologies for this problem make strong assumptions, including that the perturbation is known in advance, clean rewards are accessible, or that the perturbation preserves the optimal policy. We study a new, more general, class of unknown perturbations, and introduce a distributional reward critic framework for estimating reward distributions and perturbations during training. Our proposed methods are compatible with any RL algorithm. Despite their increased generality, we show that they achieve comparable or better rewards than existing methods in a variety of environments, including those with clean rewards. Under the challenging and generalized perturbations we study, we win/tie the highest return in 44/48 tested settings (compared to 11/48 for the best baseline). Our results broaden and deepen our ability to perform RL in reward-perturbed environments.

arXiv:2401.05525

Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) algorithms have recently made significant strides in improving network performance. Nonetheless, their practical use is still limited in the absence of safe exploration and safe decision-making. In the context of commercial solutions, reliable and safe-to-operate systems are of paramount importance. Taking this problem into account, we propose a safe learning-based load balancing algorithm for Software Defined-Wide Area Network (SD-WAN), which is empowered by Deep Reinforcement Learning (DRL) combined with a Control Barrier Function (CBF). It safely projects unsafe actions into feasible ones during both training and testing, and it guides learning towards safe policies. We successfully implemented the solution on GPU to accelerate training by approximately 110x times and achieve model updates for on-policy methods within a few seconds, making the solution practical. We show that our approach delivers near-optimal Quality-of-Service (QoS performance in terms of end-to-end delay while respecting safety requirements related to link capacity constraints. We also demonstrated that on-policy learning based on Proximal Policy Optimization (PPO) performs better than off-policy learning with Deep Deterministic Policy Gradient (DDPG) when both are combined with a CBF for safe load balancing.

arXiv:2401.05406공식 코드 · Papers with Code

RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications

Radio Frequency Reinforcement Learning (RFRL) is anticipated to be a widely applicable technology in the next generation of wireless communication systems, particularly 6G and next-gen military communications. Given this, our research is focused on developing a tool to promote the development of RFRL techniques that leverage spectrum sensing. In particular, the tool was designed to address two cognitive radio applications, specifically dynamic spectrum access and jamming. In order to train and test reinforcement learning (RL) algorithms for these applications, a simulation environment is necessary to simulate the conditions that an agent will encounter within the Radio Frequency (RF) spectrum. In this paper, such an environment has been developed, herein referred to as the RFRL Gym. Through the RFRL Gym, users can design their own scenarios to model what an RL agent may encounter within the RF spectrum as well as experiment with different spectrum sensing techniques. Additionally, the RFRL Gym is a subclass of OpenAI gym, enabling the use of third-party ML/RL Libraries. We plan to open-source this codebase to enable other researchers to utilize the RFRL Gym to test their own scenarios and RL algorithms, ultimately leading to the advancement of RL research in the wireless communications domain. This paper describes in further detail the components of the Gym, results from example scenarios, and plans for future additions. Index Terms-machine learning, reinforcement learning, wireless communications, dynamic spectrum access, OpenAI gym

arXiv:2401.05876공식 코드 · Papers with Code

Safe reinforcement learning in uncertain contexts

When deploying machine learning algorithms in the real world, guaranteeing safety is an essential asset. Existing safe learning approaches typically consider continuous variables, i.e., regression tasks. However, in practice, robotic systems are also subject to discrete, external environmental changes, e.g., having to carry objects of certain weights or operating on frozen, wet, or dry surfaces. Such influences can be modeled as discrete context variables. In the existing literature, such contexts are, if considered, mostly assumed to be known. In this work, we drop this assumption and show how we can perform safe learning when we cannot directly measure the context variables. To achieve this, we derive frequentist guarantees for multi-class classification, allowing us to estimate the current context from measurements. Further, we propose an approach for identifying contexts through experiments. We discuss under which conditions we can retain theoretical guarantees and demonstrate the applicability of our algorithm on a Furuta pendulum with camera measurements of different weights that serve as contexts.

arXiv:2401.05821공식 코드 · Papers with Code

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies. To this end, we introduce *Successive Concept Bottleneck Agents* (SCoBots), that integrate consecutive concept bottleneck (CB) layers. In contrast to current CB models, SCoBots do not just represent concepts as properties of individual objects, but also as relations between objects which is crucial for many RL tasks. Our experimental results provide evidence of SCoBots' competitive performances, but also of their potential for domain experts to understand and regularize their behavior. Among other things, SCoBots enabled us to identify a previously unknown misalignment problem in the iconic video game, Pong, and resolve it. Overall, SCoBots thus result in more human-aligned RL agents. Our code is available at https://github.com/k4ntz/SCoBots .

arXiv:2401.05794

Bounds on the price of feedback for mistake-bounded online learning

We improve several worst-case bounds for various online learning scenarios from (Auer and Long, Machine Learning, 1999). In particular, we sharpen an upper bound for delayed ambiguous reinforcement learning by a factor of 2 and an upper bound for learning compositions of families of functions by a factor of 2.41. We also improve a lower bound from the same paper for learning compositions of $k$ families of functions by a factor of $\Theta(\ln{k})$, matching the upper bound up to a constant factor. In addition, we solve a problem from (Long, Theoretical Computer Science, 2020) on the price of bandit feedback with respect to standard feedback for multiclass learning, and we improve an upper bound from (Feng et al., Theoretical Computer Science, 2023) on the price of $r$-input delayed ambiguous reinforcement learning by a factor of $r$, matching a lower bound from the same paper up to the leading term.

arXiv:2401.05572

Innate-Values-driven Reinforcement Learning based Cooperative Multi-Agent Cognitive Modeling

In multi-agent systems (MAS), the dynamic interaction among multiple decision-makers is driven by their innate values, affecting the environment's state, and can cause specific behavioral patterns to emerge. On the other hand, innate values in cognitive modeling reflect individual interests and preferences for specific tasks and drive them to develop diverse skills and plans, satisfying their various needs and achieving common goals in cooperation. Therefore, building the awareness of AI agents to balance the group utilities and system costs and meet group members' needs in their cooperation is a crucial problem for individuals learning to support their community and even integrate into human society in the long term. However, the current MAS reinforcement learning domain lacks a general intrinsic model to describe agents' dynamic motivation for decision-making and learning from an individual needs perspective in their cooperation. To address the gap, this paper proposes a general MAS innate-values reinforcement learning (IVRL) architecture from the individual preferences angle. We tested the Multi-Agent IVRL Actor-Critic Model in different StarCraft Multi-Agent Challenge (SMAC) settings, which demonstrated its potential to organize the group's behaviours to achieve better performance.

arXiv:2401.05251

ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries

Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. Furthermore, this work contributes actor regularizations that are relevant to real-world environments which differ from training. Accordingly, we apply dropout layer normalization to the actor and critic networks of the truncated quantile critic (TQC) algorithm. To show our approach's working principle and effectiveness, we train and evaluate the DRL agent on the parametrization task of an industrial control structure with parameter lookup tables.

arXiv:2401.04934

Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey

Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of information about other agents, it is challenging to derive algorithms that can converge to the optimal joint policy in a fully decentralized setting. Thus, this research area has not been thoroughly studied. In this paper, we seek to systematically review the fully decentralized methods in two settings: maximizing a shared reward of all agents and maximizing the sum of individual rewards of all agents, and discuss open questions and future research directions.

arXiv:2401.04056

A Minimaximalist Approach to Reinforcement Learning from Human Feedback

We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is therefore rather simple to implement. Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction. To achieve the preceding qualities, we build upon the concept of a Minimax Winner (MW), a notion of preference aggregation from the social choice theory literature that frames learning from preferences as a zero-sum game between two policies. By leveraging the symmetry of this game, we prove that rather than using the traditional technique of dueling two policies to compute the MW, we can simply have a single agent play against itself while maintaining strong convergence guarantees. Practically, this corresponds to sampling multiple trajectories from a policy, asking a preference or teacher model to compare them, and then using the proportion of wins as the reward for a particular trajectory. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches while maintaining robustness to the intransitive and stochastic preferences that frequently occur in practice when aggregating human judgments.

arXiv:2401.03947

Guiding drones by information gain

The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.

arXiv:2401.03896

A Tensor Network Implementation of Multi Agent Reinforcement Learning

Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques that are specific to TNs, that one can apply to ensure the most efficient representation is found. In this report, these methods are used to form a TN that represents the expected return of a multi-agent reinforcement learning (MARL) task. This model is then applied to a 2 agent random walker example, where it was shown that the policy is correctly optimised using a DMRG technique. Finally, I demonstrate the use of an exact decomposition technique, reducing the number of elements in the tensors by 97.5%, without experiencing any loss of information.

arXiv:2401.03857

Inverse Reinforcement Learning with Sub-optimal Experts

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however, it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we extend the IRL formulation to problems where, in addition to demonstrations from the optimal agent, we can observe the behavior of multiple sub-optimal experts. Given this problem, we first study the theoretical properties of the class of reward functions that are compatible with a given set of experts, i.e., the feasible reward set. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model. To this end, we analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.

arXiv:2401.03786

Long-term Safe Reinforcement Learning with Binary Feedback

Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric safety feedback; 2) does not guarantee safety during the learning process; 3) limits the problem to a priori known, deterministic transition dynamics; and/or 4) assume the existence of a known safe policy for any states. Addressing the issues mentioned above, we thus propose Long-term Binaryfeedback Safe RL (LoBiSaRL), a safe RL algorithm for constrained Markov decision processes (CMDPs) with binary safety feedback and an unknown, stochastic state transition function. LoBiSaRL optimizes a policy to maximize rewards while guaranteeing a long-term safety that an agent executes only safe state-action pairs throughout each episode with high probability. Specifically, LoBiSaRL models the binary safety function via a generalized linear model (GLM) and conservatively takes only a safe action at every time step while inferring its effect on future safety under proper assumptions. Our theoretical results show that LoBiSaRL guarantees the long-term safety constraint, with high probability. Finally, our empirical results demonstrate that our algorithm is safer than existing methods without significantly compromising performance in terms of reward.

arXiv:2401.03137공식 코드 · Papers with Code

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Alleviating overestimation bias is a critical challenge for deep reinforcement learning to achieve successful performance on more complex tasks or offline datasets containing out-of-distribution data. In order to overcome overestimation bias, ensemble methods for Q-learning have been investigated to exploit the diversity of multiple Q-functions. Since network initialization has been the predominant approach to promote diversity in Q-functions, heuristically designed diversity injection methods have been studied in the literature. However, previous studies have not attempted to approach guaranteed independence over an ensemble from a theoretical perspective. By introducing a novel regularization loss for Q-ensemble independence based on random matrix theory, we propose spiked Wishart Q-ensemble independence regularization (SPQR) for reinforcement learning. Specifically, we modify the intractable hypothesis testing criterion for the Q-ensemble independence into a tractable KL divergence between the spectral distribution of the Q-ensemble and the target Wigner's semicircle distribution. We implement SPQR in several online and offline ensemble Q-learning algorithms. In the experiments, SPQR outperforms the baseline algorithms in both online and offline RL benchmarks.