Time-critical control applications typically pose stringent connectivity requirements for communication networks. The imperfections associated with the wireless medium such as packet losses, synchronization errors, and varying delays have a detrimental effect on performance of real-time control, often with safety implications. This paper introduces multi-service edge-intelligence as a new paradigm for realizing time-critical control over wireless. It presents the concept of multi-service edge-intelligence which revolves around tight integration of wireless access, edge-computing and machine learning techniques, in order to provide stability guarantees under wireless imperfections. The paper articulates some of the key system design aspects of multi-service edge-intelligence. It also presents a temporal-adaptive prediction technique to cope with dynamically changing wireless environments. It provides performance results in a robotic teleoperation scenario. Finally, it discusses some open research and design challenges for multi-service edge-intelligence.
Generative models for learning combinatorial structures have transformative impacts in many applications. However, existing approaches fail to offer efficient and accurate learning results. Because of the highly intractable nature of the gradient estimation of the learning objective subject to combinatorial constraints. Existing gradient estimation methods would easily run into exponential time/memory space, or incur huge estimation errors due to improper approximation. We develop NEural Lovasz Sampler (Nelson), a neural network based on Lov\'asz Local Lemma (LLL). We show it guarantees to generate samples satisfying combinatorial constraints from the distribution of the constrained Markov Random Fields model (MRF) under certain conditions. We further present a fully differentiable contrastive-divergence-based learning framework on constrained MRF (Nelson-CD). Meanwhile, Nelson-CD being fully differentiable allows us to take advantage of the parallel computing power of GPUs, resulting in great efficiency. Experimental results on three real-world combinatorial problems reveal that Nelson learns to generate 100% valid structures. In comparison, baselines either time out on large-size data sets or fail to generate valid structures, whereas Nelson scales much better with problem size. In addition, Nelson outperforms baselines in various learning metrics, such as log-likelihood and MAP scores.
We propose a new model-based offline RL framework, called Adversarial Models for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary baseline policy regardless of data coverage. Based on the concept of relative pessimism, ARMOR is designed to optimize for the worst-case relative performance when facing uncertainty. In theory, we prove that the learned policy of ARMOR never degrades the performance of the baseline policy with any admissible hyperparameter, and can learn to compete with the best policy within data coverage when the hyperparameter is well tuned, and the baseline policy is supported by the data. Such a robust policy improvement property makes ARMOR especially suitable for building real-world learning systems, because in practice ensuring no performance degradation is imperative before considering any benefit learning can bring.
Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function (or other functions of interest, such as density ratios). While recent works on marginalized importance sampling (MIS) show that the former can enjoy provable guarantees under realizable function approximation, the latter is only known to be feasible under much stronger assumptions such as prohibitively expressive discriminators. In this work, we provide guarantees for off-policy function estimation under only realizability, by imposing proper regularization on the MIS objectives. Compared to commonly used regularization in MIS, our regularizer is much more flexible and can account for an arbitrary user-specified distribution, under which the learned function will be close to the groundtruth. We provide exact characterization of the optimal dual solution that needs to be realized by the discriminator class, which determines the data-coverage assumption in the case of value-function learning. As another surprising observation, the regularizer can be altered to relax the data-coverage requirement, and completely eliminate it in the ideal case with strong side information.
Coverage conditions -- which assert that the data logging distribution adequately covers the state space -- play a fundamental role in determining the sample complexity of offline reinforcement learning. While such conditions might seem irrelevant to online reinforcement learning at first glance, we establish a new connection by showing -- somewhat surprisingly -- that the mere existence of a data distribution with good coverage can enable sample-efficient online RL. Concretely, we show that coverability -- that is, existence of a data distribution that satisfies a ubiquitous coverage condition called concentrability -- can be viewed as a structural property of the underlying MDP, and can be exploited by standard algorithms for sample-efficient exploration, even when the agent does not know said distribution. We complement this result by proving that several weaker notions of coverage, despite being sufficient for offline RL, are insufficient for online RL. We also show that existing complexity measures for online RL, including Bellman rank and Bellman-Eluder dimension, fail to optimally capture coverability, and propose a new complexity measure, the sequential extrapolation coefficient, to provide a unification.
We consider text retrieval within dense representational space in real-world settings such as e-commerce search where (a) document popularity and (b) diversity of queries associated with a document have a skewed distribution. Most of the contemporary dense retrieval literature presents two shortcomings in these settings. (1) They learn an almost equal number of representations per document, agnostic to the fact that a few head documents are disproportionately more critical to achieving a good retrieval performance. (ii) They learn purely semantic document representations inferred from intrinsic document characteristics which may not contain adequate information to determine the queries for which the document is relevant--especially when the document is short. We propose to overcome these limitations by augmenting semantic document representations learned by bi-encoders with behavioral document representations learned by our proposed approach MVG. To do so, MVG (1) determines how to divide the total budget for behavioral representations by drawing a connection to the Pitman-Yor process, and (2) simply clusters the queries related to a given document (based on user behavior) within the representational space learned by a base bi-encoder, and treats the cluster centers as its behavioral representations. Our central contribution is the finding such a simple intuitive light-weight approach leads to substantial gains in key first-stage retrieval metrics by incurring only a marginal memory overhead. We establish this via extensive experiments over three large public datasets comparing several single-vector and multi-vector bi-encoders, a proprietary e-commerce search dataset compared to production-quality bi-encoder, and an A/B test.
We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the curse of horizon in POMDPs. To circumvent this problem, we develop a novel model-free OPE method by introducing future-dependent value functions that take future proxies as inputs. Future-dependent value functions play similar roles as classical value functions in fully-observable MDPs. We derive a new Bellman equation for future-dependent value functions as conditional moment equations that use history proxies as instrumental variables. We further propose a minimax learning method to learn future-dependent value functions using the new Bellman equation. We obtain the PAC result, which implies our OPE estimator is consistent as long as futures and histories contain sufficient information about latent states, and the Bellman completeness. Finally, we extend our methods to learning of dynamics and establish the connection between our approach and the well-known spectral learning methods in POMDPs.
The current paper studies sample-efficient Reinforcement Learning (RL) in settings where only the optimal value function is assumed to be linearly-realizable. It has recently been understood that, even under this seemingly strong assumption and access to a generative model, worst-case sample complexities can be prohibitively (i.e., exponentially) large. We investigate the setting where the learner additionally has access to interactive demonstrations from an expert policy, and we present a statistically and computationally efficient algorithm (Delphi) for blending exploration with expert queries. In particular, Delphi requires $\tilde{\mathcal{O}}(d)$ expert queries and a $\texttt{poly}(d,H,|\mathcal{A}|,1/\varepsilon)$ amount of exploratory samples to provably recover an $\varepsilon$-suboptimal policy. Compared to pure RL approaches, this corresponds to an exponential improvement in sample complexity with surprisingly-little expert input. Compared to prior imitation learning (IL) approaches, our required number of expert demonstrations is independent of $H$ and logarithmic in $1/\varepsilon$, whereas all prior work required at least linear factors of both in addition to the same dependence on $d$. Towards establishing the minimal amount of expert queries needed, we show that, in the same setting, any learner whose exploration budget is polynomially-bounded (in terms of $d,H,$ and $|\mathcal{A}|$) will require at least $\tilde\Omega(\sqrt{d})$ oracle calls to recover a policy competing with the expert's value function. Under the weaker assumption that the expert's policy is linear, we show that the lower bound increases to $\tilde\Omega(d)$.
We study reward-free reinforcement learning (RL) under general non-linear function approximation, and establish sample efficiency and hardness results under various standard structural assumptions. On the positive side, we propose the RFOLIVE (Reward-Free OLIVE) algorithm for sample-efficient reward-free exploration under minimal structural assumptions, which covers the previously studied settings of linear MDPs (Jin et al., 2020b), linear completeness (Zanette et al., 2020b) and low-rank MDPs with unknown representation (Modi et al., 2021). Our analyses indicate that the explorability or reachability assumptions, previously made for the latter two settings, are not necessary statistically for reward-free exploration. On the negative side, we provide a statistical hardness result for both reward-free and reward-aware exploration under linear completeness assumptions when the underlying features are unknown, showing an exponential separation between low-rank and linear completeness settings.