The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic algorithms, but average reward off-policy actor-critic is relatively less explored. In this work, we present both on-policy and off-policy deterministic policy gradient theorems for the average reward performance criterion. Using these theorems, we also present an Average Reward Off-Policy Deep Deterministic Policy Gradient (ARO-DDPG) Algorithm. We first show asymptotic convergence analysis using the ODE-based method. Subsequently, we provide a finite time analysis of the resulting stochastic approximation scheme with linear function approximator and obtain an $\epsilon$-optimal stationary policy with a sample complexity of $\Omega(\epsilon^{-2.5})$. We compare the average reward performance of our proposed ARO-DDPG algorithm and observe better empirical performance compared to state-of-the-art on-policy average reward actor-critic algorithms over MuJoCo-based environments.
相關內容
In the realm of expressive Text-to-Speech (TTS), explicit prosodic boundaries significantly advance the naturalness and controllability of synthesized speech. While human prosody annotation contributes a lot to the performance, it is a labor-intensive and time-consuming process, often resulting in inconsistent outcomes. Despite the availability of extensive supervised data, the current benchmark model still faces performance setbacks. To address this issue, a two-stage automatic annotation pipeline is novelly proposed in this paper. Specifically, in the first stage, we propose contrastive text-speech pretraining of Speech-Silence and Word-Punctuation (SSWP) pairs. The pretraining procedure hammers at enhancing the prosodic space extracted from joint text-speech space. In the second stage, we build a multi-modal prosody annotator, which consists of pretrained encoders, a straightforward yet effective text-speech feature fusion scheme, and a sequence classifier. Extensive experiments conclusively demonstrate that our proposed method excels at automatically generating prosody annotation and achieves state-of-the-art (SOTA) performance. Furthermore, our novel model has exhibited remarkable resilience when tested with varying amounts of data.
We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech. During inference, our method only uses a stream of speech signals to perform unimodal SER thus reducing computation overhead and avoiding run-time transcription and prosodic feature extraction errors. During training, our method distills information at both embedding and logit levels from a pair of pre-trained Prosodic and Linguistic teachers that are fine-tuned for SER. Experiments on the IEMOCAP benchmark demonstrate that our method outperforms other unimodal and multimodal techniques by a considerable margin, and achieves state-of-the-art performance of 77.49% unweighted accuracy and 78.91% weighted accuracy. Detailed ablation studies demonstrate the impact of each component of our method.
Refractive Index Tomography is an inverse problem in which we seek to reconstruct a scene's 3D refractive field from 2D projected image measurements. The refractive field is not visible itself, but instead affects how the path of a light ray is continuously curved as it travels through space. Refractive fields appear across a wide variety of scientific applications, from translucent cell samples in microscopy to fields of dark matter bending light from faraway galaxies. This problem poses a unique challenge because the refractive field directly affects the path that light takes, making its recovery a non-linear problem. In addition, in contrast with traditional tomography, we seek to recover the refractive field using a projected image from only a single viewpoint by leveraging knowledge of light sources scattered throughout the medium. In this work, we introduce a method that uses a coordinate-based neural network to model the underlying continuous refractive field in a scene. We then use explicit modeling of rays' 3D spatial curvature to optimize the parameters of this network, reconstructing refractive fields with an analysis-by-synthesis approach. The efficacy of our approach is demonstrated by recovering refractive fields in simulation, and analyzing how recovery is affected by the light source distribution. We then test our method on a simulated dark matter mapping problem, where we recover the refractive field underlying a realistic simulated dark matter distribution.
Synthesizing interaction-involved human motions has been challenging due to the high complexity of 3D environments and the diversity of possible human behaviors within. We present LAMA, Locomotion-Action-MAnipulation, to synthesize natural and plausible long-term human movements in complex indoor environments. The key motivation of LAMA is to build a unified framework to encompass a series of everyday motions including locomotion, scene interaction, and object manipulation. Unlike existing methods that require motion data "paired" with scanned 3D scenes for supervision, we formulate the problem as a test-time optimization by using human motion capture data only for synthesis. LAMA leverages a reinforcement learning framework coupled with a motion matching algorithm for optimization, and further exploits a motion editing framework via manifold learning to cover possible variations in interaction and manipulation. Throughout extensive experiments, we demonstrate that LAMA outperforms previous approaches in synthesizing realistic motions in various challenging scenarios. Project page: //jiyewise.github.io/projects/LAMA/ .
With the rapid evolution and diversification of Internet applications, their communication-quality criteria are continuously evolving. To globally optimize communication quality, the Internet's control plane thus needs to optimize inter-domain paths on diverse criteria, and should provide flexibility for adding new criteria or modifying existing ones. However, existing inter-domain routing protocols and proposals satisfy these requirements at best to a limited degree. We propose IREC, an inter-domain routing architecture that enables multi-criteria path optimization with extensible criteria through parallel execution and real-time addition of independent routing algorithms, together with the possibility for end domains to express their desired criteria to the control plane. We show IREC's viability by implementing it on a global testbed, and use simulations on a realistic Internet topology to demonstrate IREC's potential for path optimization in real-world deployments.
Since the origins of the Internet, various vulnerabilities exploiting the IP fragmentation process have plagued IPv4 protocol, many leading to a wide range of attacks. IPv6 modified the handling of fragmentations and introduced a specific extension header, not solving the related problems, as proved by extensive literature. One of the primary sources of problems has been the overlapping fragments, which result in unexpected or malicious packets when reassembled. To overcome the problem related to fragmentation, the authors of RFC 5722 decided that IPv6 hosts MUST silently drop overlapping fragments. Since then, several studies have proposed methodologies to check if IPv6 hosts accept overlapping fragments and are still vulnerable to related attacks. However, some of the above methodologies have not been proven complete or need to be more accurate. In this paper we propose a novel model to check IPv6 fragmentation handling specifically suited for the reassembling strategies of modern operating systems. Previous models, indeed, considered OS reassembly policy as byte-based. However, nowadays, reassembly policies are fragment-based, making previous models inadequate. Our model leverages the commutative property of the checksum, simplifying the whole assessing process. Starting with this new model, we were able to better evaluate the RFC-5722 and RFC-9099 compliance of modern operating systems against fragmentation handling. Our results suggest that IPv6 fragmentation can still be considered a threat and that more effort is needed to solve related security issues.
Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. However, it has been noted that maximizing the log-likelihood within an energy-based setting can lead to an adversarial framework where the discriminator provides unnormalized density (often called energy). We further develop this perspective, incorporate importance sampling, and show that 1) Wasserstein GAN performs a biased estimate of the partition function, and we propose instead to use an unbiased estimator; and 2) when optimizing for likelihood, one must maximize generator entropy. This is hypothesized to provide a better mode coverage. Different from previous works, we explicitly compute the density of the generated samples. This is the key enabler to designing an unbiased estimator of the partition function and computation of the generator entropy term. The generator density is obtained via a new type of flow network, called one-way flow network, that is less constrained in terms of architecture, as it does not require a tractable inverse function. Our experimental results show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data.
Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes compared to conventional KBs (18x more nodes in ATOMIC compared to Freebase (FB15K-237)). Importantly, this implies significantly sparser graph structures - a major challenge for existing KB completion methods that assume densely connected graphs over a relatively smaller set of nodes. In this paper, we present novel KB completion models that can address these challenges by exploiting the structural and semantic context of nodes. Specifically, we investigate two key ideas: (1) learning from local graph structure, using graph convolutional networks and automatic graph densification and (2) transfer learning from pre-trained language models to knowledge graphs for enhanced contextual representation of knowledge. We describe our method to incorporate information from both these sources in a joint model and provide the first empirical results for KB completion on ATOMIC and evaluation with ranking metrics on ConceptNet. Our results demonstrate the effectiveness of language model representations in boosting link prediction performance and the advantages of learning from local graph structure (+1.5 points in MRR for ConceptNet) when training on subgraphs for computational efficiency. Further analysis on model predictions shines light on the types of commonsense knowledge that language models capture well.
We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convolutional neural nets are surprisingly effective descriptors for this specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to segmentation labels and aerial photos to map images. Finally, we introduce a discriminatively trained variant and fine-tune our system through our proposed metric, obtaining state-of-the-art performance.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis.
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