اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDifferential Advising in Multi-Agent Reinforcement Learning
153
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Agent advising is one of the main approaches to improve agent learning performance by enabling agents to share advice. Existing advising methods have a common limitation that an adviser agent can offer advice to an advisee agent only if the advice is created in the same state as the advisees concerned state. However, in complex environments, it is a very strong requirement that two states are the same, because a state may consist of multiple dimensions and two states being the same means that all these dimensions in the two states are correspondingly identical. Therefore, this requirement may limit the applicability of existing advising methods to complex environments. In this paper, inspired by the differential privacy scheme, we propose a differential advising method which relaxes this requirement by enabling agents to use advice in a state even if the advice is created in a slightly different state. Compared with existing methods, agents using the proposed method have more opportunity to take advice from others. This paper is the first to adopt the concept of differential privacy on advising to improve agent learning performance instead of addressing security issues. The experimental results demonstrate that the proposed method is more efficient in complex environments than existing methods.
قيم البحث
اقرأ أيضاً
Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents ability to coordinate their behaviour. In this paper, we show that common knowledge between agents allows for complex decentralised
coordination. Common knowledge arises naturally in a large number of decentralised cooperative multi-agent tasks, for example, when agents can reconstruct parts of each others observations. Since agents an independently agree on their common knowledge, they can execute complex coordinated policies that condition on this knowledge in a fully decentralised fashion. We propose multi-agent common knowledge reinforcement learning (MACKRL), a novel stochastic actor-critic algorithm that learns a hierarchical policy tree. Higher levels in the hierarchy coordinate groups of agents by conditioning on their common knowledge, or delegate to lower levels with smaller subgroups but potentially richer common knowledge. The entire policy tree can be executed in a fully decentralised fashion. As the lowest policy tree level consists of independent policies for each agent, MACKRL reduces to independently learnt decentralised policies as a special case. We demonstrate that our method can exploit common knowledge for superior performance on complex decentralised coordination tasks, including a stochastic matrix game and challenging problems in StarCraft II unit micromanagement.
Matrix games like Prisoners Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Coope
rativeness is a property that applies to policies, not elementary actions. We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions. We analyze the dynamics of policies learned by multiple self-interested independent learning agents, each using its own deep Q-network, on two Markov games we introduce here: 1. a fruit Gathering game and 2. a Wolfpack hunting game. We characterize how learned behavior in each domain changes as a function of environmental factors including resource abundance. Our experiments show how conflict can emerge from competition over shared resources and shed light on how the sequential nature of real world social dilemmas affects cooperation.
In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary proble
m in training, their decentralized execution paradigm limits the agents capability to coordinate. Inspired by the concept of correlated equilibrium, we propose to introduce a coordination signal to address this limitation, and theoretically show that following mild conditions, decentralized agents with the coordination signal can coordinate their individual policies as manipulated by a centralized controller. The idea of introducing coordination signal is to encapsulate coordinated strategies into the signals, and use the signals to instruct the collaboration in decentralized execution. To encourage agents to learn to exploit the coordination signal, we propose Signal Instructed Coordination (SIC), a novel coordination module that can be integrated with most existing MARL frameworks. SIC casts a common signal sampled from a pre-defined distribution to all agents, and introduces an information-theoretic regularization to facilitate the consistency between the observed signal and agents policies. Our experiments show that SIC consistently improves performance over well-recognized MARL models in both matrix games and a predator-prey game with high-dimensional strategy space.
We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such comm
unication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.
Unsupervised skill discovery drives intelligent agents to explore the unknown environment without task-specific reward signal, and the agents acquire various skills which may be useful when the agents adapt to new tasks. In this paper, we propose Mul
ti-agent Skill Discovery(MASD), a method for discovering skills for coordination patterns of multiple agents. The proposed method aims to maximize the mutual information between a latent code Z representing skills and the combination of the states of all agents. Meanwhile it suppresses the empowerment of Z on the state of any single agent by adversarial training. In another word, it sets an information bottleneck to avoid empowerment degeneracy. First we show the emergence of various skills on the level of coordination in a general particle multi-agent environment. Second, we reveal that the bottleneck prevents skills from collapsing to a single agent and enhances the diversity of learned skills. Finally, we show the pretrained policies have better performance on supervised RL tasks.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
