Recently, model-based agents have achieved better performance compared with model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is very difficult to learn the model of the environment. When model-based methods are applied to multi-agent tasks, the significant compounding error may hinder the learning process. In this paper, we propose an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states, which makes agents have foresight. Our method can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in partially observable Markov decision process domains.
相關內容
Multi-agent deep reinforcement learning has been applied to address a variety of complex problems with either discrete or continuous action spaces and achieved great success. However, most real-world environments cannot be described by only discrete action spaces or only continuous action spaces. And there are few works having ever utilized deep reinforcement learning (drl) to multi-agent problems with hybrid action spaces. Therefore, we propose a novel algorithm: Deep Multi-Agent Hybrid Soft Actor-Critic (MAHSAC) to fill this gap. This algorithm follows the centralized training but decentralized execution (CTDE) paradigm, and extend the Soft Actor-Critic algorithm (SAC) to handle hybrid action space problems in Multi-Agent environments based on maximum entropy. Our experiences are running on an easy multi-agent particle world with a continuous observation and discrete action space, along with some basic simulated physics. The experimental results show that MAHSAC has good performance in training speed, stability, and anti-interference ability. At the same time, it outperforms existing independent deep hybrid learning method in cooperative scenarios and competitive scenarios.
Deep Reinforcement Learning has demonstrated the potential of neural networks tuned with gradient descent for solving complex tasks in well-delimited environments. However, these neural systems are slow learners producing specialised agents with no mechanism to continue learning beyond their training curriculum. On the contrary, biological synaptic plasticity is persistent and manifold, and has been hypothesised to play a key role in executive functions such as working memory and cognitive flexibility, potentially supporting more efficient and generic learning abilities. Inspired by this, we propose to build networks with dynamic weights, able to continually perform self-reflexive modification as a function of their current synaptic state and action-reward feedback, rather than a fixed network configuration. The resulting model, MetODS (for Meta-Optimized Dynamical Synapses) is a broadly applicable meta-reinforcement learning system able to learn efficient and powerful control rules in the agent policy space. A single layer with dynamic synapses can perform one-shot learning, generalize navigation principles to unseen environments and demonstrate a strong ability to learn adaptive motor policies, comparing favourably with previous meta-reinforcement learning approaches.
Offline policy evaluation (OPE) is considered a fundamental and challenging problem in reinforcement learning (RL). This paper focuses on the value estimation of a target policy based on pre-collected data generated from a possibly different policy, under the framework of infinite-horizon Markov decision processes. Motivated by the recently developed marginal importance sampling method in RL and the covariate balancing idea in causal inference, we propose a novel estimator with approximately projected state-action balancing weights for the policy value estimation. We obtain the convergence rate of these weights and show that the proposed value estimator is semi-parametric efficient under technical conditions. In terms of asymptotics, our results scale with both the number of trajectories and the number of decision points at each trajectory. As such, consistency can still be achieved with a limited number of subjects when the number of decision points diverges. In addition, we develop a necessary and sufficient condition for establishing the well-posedness of the Bellman operator in the off-policy setting, which characterizes the difficulty of OPE and may be of independent interest. Numerical experiments demonstrate the promising performance of our proposed estimator.
The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information $Z$ from past transition segments to make the dynamics prediction model generalizable to different dynamics. However, because environments are not labelled, the extracted information inevitably contains redundant information unrelated to the dynamics in transition segments and thus fails to maintain a crucial property of $Z$: $Z$ should be similar in the same environment and dissimilar in different ones. As a result, the learned dynamics prediction function will deviate from the true one, which undermines the generalization ability. To tackle this problem, we introduce an interventional prediction module to estimate the probability of two estimated $\hat{z}_i, \hat{z}_j$ belonging to the same environment. Furthermore, by utilizing the $Z$'s invariance within a single environment, a relational head is proposed to enforce the similarity between $\hat{{Z}}$ from the same environment. As a result, the redundant information will be reduced in $\hat{Z}$. We empirically show that $\hat{{Z}}$ estimated by our method enjoy less redundant information than previous methods, and such $\hat{{Z}}$ can significantly reduce dynamics prediction errors and improve the performance of model-based RL methods on zero-shot new environments with unseen dynamics. The codes of this method are available at \url{//github.com/CR-Gjx/RIA}.
This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data. Specifically, consider a $\gamma$-discounted infinite-horizon Markov game with $S$ states, where the max-player has $A$ actions and the min-player has $B$ actions. We propose a pessimistic model-based algorithm with Bernstein-style lower confidence bounds -- called VI-LCB-Game -- that provably finds an $\varepsilon$-approximate Nash equilibrium with a sample complexity no larger than $\frac{C_{\mathsf{clipped}}^{\star}S(A+B)}{(1-\gamma)^{3}\varepsilon^{2}}$ (up to some log factor). Here, $C_{\mathsf{clipped}}^{\star}$ is some unilateral clipped concentrability coefficient that reflects the coverage and distribution shift of the available data (vis-\`a-vis the target data), and the target accuracy $\varepsilon$ can be any value within $\big(0,\frac{1}{1-\gamma}\big]$. Our sample complexity bound strengthens prior art by a factor of $\min\{A,B\}$, achieving minimax optimality for the entire $\varepsilon$-range. An appealing feature of our result lies in algorithmic simplicity, which reveals the unnecessity of variance reduction and sample splitting in achieving sample optimality.
Motivated by the recent empirical success of policy-based reinforcement learning (RL), there has been a research trend studying the performance of policy-based RL methods on standard control benchmark problems. In this paper, we examine the effectiveness of policy-based RL methods on an important robust control problem, namely $\mu$ synthesis. We build a connection between robust adversarial RL and $\mu$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $\mu$ synthesis with static $D$-scaling. In the proposed algorithm, the $K$ step mimics the classical central path algorithm via incorporating a recently-developed double-loop adversarial RL method as a subroutine, and the $D$ step is based on model-free finite difference approximation. Extensive numerical study is also presented to demonstrate the utility of our proposed model-free algorithm. Our study sheds new light on the connections between adversarial RL and robust control.
Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage. But due to the limitation under the offline setting, the learned model could not mimic real dynamics well enough to support reliable out-of-distribution exploration, which still hinders policy to generalize well. To narrow the gap, previous works roughly ensemble randomly initialized models to better approximate the real dynamics. However, such practice is costly and inefficient, and provides no guarantee on how well the real dynamics could be approximated by the learned models, which we name coverability in this paper. We actively address this issue by generating models with provable ability to cover real dynamics in an efficient and controllable way. To that end, we design a distance metric for dynamic models based on the occupancy of policies under the dynamics, and propose an algorithm to generate models optimizing their coverage for the real dynamics. We give a theoretical analysis on the model generation process and proves that our algorithm could provide enhanced coverability. As a downstream task, we train a dynamics-aware policy with minor or no conservative penalty, and experiments demonstrate that our algorithm outperforms prior offline methods on existing offline RL benchmarks. We also discover that policies learned by our method have better zero-shot transfer performance, implying their better generalization.
Many deep reinforcement learning algorithms rely on simple forms of exploration, such as the additive action-noise often used in continuous control domains. Typically, the scaling factor of this action noise is chosen as a hyper-parameter and kept constant during training. In this paper, we analyze how the learned policy is impacted by the noise type, scale, and reducing of the scaling factor over time. We consider the two most prominent types of action-noise: Gaussian and Ornstein-Uhlenbeck noise, and perform a vast experimental campaign by systematically varying the noise type and scale parameter, and by measuring variables of interest like the expected return of the policy and the state space coverage during exploration. For the latter, we propose a novel state-space coverage measure $\operatorname{X}_{\mathcal{U}\text{rel}}$ that is more robust to boundary artifacts than previously proposed measures. Larger noise scales generally increase state space coverage. However, we found that increasing the space coverage using a larger noise scale is often not beneficial. On the contrary, reducing the noise-scale over the training process reduces the variance and generally improves the learning performance. We conclude that the best noise-type and scale are environment dependent, and based on our observations, derive heuristic rules for guiding the choice of the action noise as a starting point for further optimization.
Recommender systems (RSs) have become an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered to be a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem can better reflect the user-system interaction. Therefore, it can be formulated as a Markov decision process (MDP) and be solved by reinforcement learning (RL) algorithms. Unlike traditional recommendation methods, including collaborative filtering and content-based filtering, RL is able to handle the sequential, dynamic user-system interaction and to take into account the long-term user engagement. Although the idea of using RL for recommendation is not new and has been around for about two decades, it was not very practical, mainly because of scalability problems of traditional RL algorithms. However, a new trend has emerged in the field since the introduction of deep reinforcement learning (DRL), which made it possible to apply RL to the recommendation problem with large state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. Our aim is to present an outlook on the field and to provide the reader with a fairly complete knowledge of key concepts of the field. We first recognize and illustrate that RLRSs can be generally classified into RL- and DRL-based methods. Then, we propose an RLRS framework with four components, i.e., state representation, policy optimization, reward formulation, and environment building, and survey RLRS algorithms accordingly. We highlight emerging topics and depict important trends using various graphs and tables. Finally, we discuss important aspects and challenges that can be addressed in the future.
This paper focuses on improving the resource allocation algorithm in terms of packet delivery ratio (PDR), i.e., the number of successfully received packets sent by end devices (EDs) in a long-range wide-area network (LoRaWAN). Setting the transmission parameters significantly affects the PDR. Employing reinforcement learning (RL), we propose a resource allocation algorithm that enables the EDs to configure their transmission parameters in a distributed manner. We model the resource allocation problem as a multi-armed bandit (MAB) and then address it by proposing a two-phase algorithm named MIX-MAB, which consists of the exponential weights for exploration and exploitation (EXP3) and successive elimination (SE) algorithms. We evaluate the MIX-MAB performance through simulation results and compare it with other existing approaches. Numerical results show that the proposed solution performs better than the existing schemes in terms of convergence time and PDR.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191