Learning to collaborate is critical in multi-agent reinforcement learning (MARL). A number of previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterised by mutual information (MI) in different forms. However, in this paper, we reveal that strong correlation can emerge from sub-optimal collaborative behaviors, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration. To address this issue, we propose a novel MARL framework, called Progressive Mutual Information Collaboration (PMIC), for more effective MI-driven collaboration. In PMIC, we use a new collaboration criterion measured by the MI between global states and joint actions. Based on the criterion, the key idea of PMIC is maximizing the MI associated with superior collaborative behaviors and minimizing the MI associated with inferior ones. The two MI objectives play complementary roles by facilitating learning towards better collaborations while avoiding falling into sub-optimal ones. Specifically, PMIC stores and progressively maintains sets of superior and inferior interaction experiences, from which dual MI neural estimators are established. Experiments on a wide range of MARL benchmarks show the superior performance of PMIC compared with other algorithms.
Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes will destroy the cooperation among agents, leading to performance degradation. In this work, we present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes. To enhance the robustness of the system to crashes, we propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training. We design three coaching strategies and the re-sampling strategy for our coach agent. To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system. Extensive experiments on grid-world and StarCraft II micromanagement tasks demonstrate the efficacy of adaptive strategy compared with the fixed crash rate strategy and curriculum learning strategy. The ablation study further illustrates the effectiveness of our re-sampling strategy.
Multi-agent reinforcement learning suffers from poor sample efficiency due to the exponential growth of the state-action space. Considering a homogeneous multiagent system, a global state consisting of $m$ homogeneous components has $m!$ differently ordered representations, thus designing functions satisfying permutation invariant (PI) can reduce the state space by a factor of $\frac{1}{m!}$. However, mainstream MARL algorithms ignore this property and learn over the original state space. To achieve PI, previous works including data augmentation based methods and embedding-sharing architecture based methods, suffer from training instability and limited model capacity. In this work, we propose two novel designs to achieve PI, while avoiding the above limitations. The first design permutes the same but differently ordered inputs back to the same order and the downstream networks only need to learn function mapping over fixed-ordering inputs instead of all permutations, which is much easier to train. The second design applies a hypernetwork to generate customized embedding for each component, which has higher representational capacity than the previous embedding-sharing method. Empirical results on the SMAC benchmark show that the proposed method achieves 100% win-rates in almost all hard and super-hard scenarios (never achieved before), and superior sample-efficiency than the state-of-the-art baselines by up to 400%.
Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions. However, existing solutions only learn to extract a state-to-action mapping policy from the data, without considering how the expert plans to the target. This hinders the ability to leverage demonstrations and limits the flexibility of the policy. In this paper, we introduce Decoupled Policy Optimization (DePO), which explicitly decouples the policy as a high-level state planner and an inverse dynamics model. With embedded decoupled policy gradient and generative adversarial training, DePO enables knowledge transfer to different action spaces or state transition dynamics, and can generalize the planner to out-of-demonstration state regions. Our in-depth experimental analysis shows the effectiveness of DePO on learning a generalized target state planner while achieving the best imitation performance. We demonstrate the appealing usage of DePO for transferring across different tasks by pre-training, and the potential for co-training agents with various skills.
It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing the correlation (or its proxy) between features and the downstream task (labels), which typically results in a representation containing cause, effect and spurious correlated variables of the label. Its generalizability may deteriorate because of the unstability of the non-causal parts. In this paper, we propose to learn causal representation from observational data by regularizing the learning procedure with mutual information measures according to our hypothetical causal graph. The optimization involves a counterfactual loss, based on which we deduce a theoretical guarantee that the causality-inspired learning is with reduced sample complexity and better generalization ability. Extensive experiments show that the models trained on causal representations learned by our approach is robust under adversarial attacks and distribution shift.
In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards. In the absence of individual reward signals, credit assignment mechanisms are usually introduced to discriminate the contributions of different agents so as to achieve effective cooperation. Recently, the value decomposition paradigm has been widely adopted to realize credit assignment, and QMIX has become the state-of-the-art solution. In this paper, we revisit QMIX from two aspects. First, we propose a new perspective on credit assignment measurement and empirically show that QMIX suffers limited discriminability on the assignment of credits to agents. Second, we propose a gradient entropy regularization with QMIX to realize a discriminative credit assignment, thereby improving the overall performance. The experiments demonstrate that our approach can comparatively improve learning efficiency and achieve better performance.
The Dynamic Pickup and Delivery Problem (DPDP) is an essential problem within the logistics domain. So far, research on this problem has mainly focused on using artificial data which fails to reflect the complexity of real-world problems. In this draft, we would like to introduce a new benchmark from real business scenarios as well as a simulator supporting the dynamic evaluation. The benchmark and simulator have been published and successfully supported the ICAPS 2021 Dynamic Pickup and Delivery Problem competition participated by 152 teams.
Debiased recommendation has recently attracted increasing attention from both industry and academic communities. Traditional models mostly rely on the inverse propensity score (IPS), which can be hard to estimate and may suffer from the high variance issue. To alleviate these problems, in this paper, we propose a novel debiased recommendation framework based on user feature balancing. The general idea is to introduce a projection function to adjust user feature distributions, such that the ideal unbiased learning objective can be upper bounded by a solvable objective purely based on the offline dataset. In the upper bound, the projected user distributions are expected to be equal given different items. From the causal inference perspective, this requirement aims to remove the causal relation from the user to the item, which enables us to achieve unbiased recommendation, bypassing the computation of IPS. In order to efficiently balance the user distributions upon each item pair, we propose three strategies, including clipping, sampling and adversarial learning to improve the training process. For more robust optimization, we deploy an explicit model to capture the potential latent confounders in recommendation systems. To the best of our knowledge, this paper is the first work on debiased recommendation based on confounder balancing. In the experiments, we compare our framework with many state-of-the-art methods based on synthetic, semi-synthetic and real-world datasets. Extensive experiments demonstrate that our model is effective in promoting the recommendation performance.
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion. In particular, we argue that interpretable RL may embrace different facets: interpretable inputs, interpretable (transition/reward) models, and interpretable decision-making. Based on this scheme, we summarize and analyze recent work related to interpretable RL with an emphasis on papers published in the past 10 years. We also discuss briefly some related research areas and point to some potential promising research directions.