We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns defined on different policies and environment dynamics. Based on this lemma, we propose two new algorithms referred to as Relative Policy Optimization (RPO) and Relative Transition Optimization (RTO), which offer fast policy transfer and dynamics modelling, respectively. RPO transfers the policy evaluated in one environment to maximize the return in another, while RTO updates the parameterized dynamics model to reduce the gap between the dynamics of the two environments. Integrating the two algorithms results in the complete Relative Policy-Transition Optimization (RPTO) algorithm, in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer. We demonstrate the effectiveness of RPTO on a set of MuJoCo continuous control tasks by creating policy transfer problems via variant dynamics.
相關內容
Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to potential parameter alterations. In this study, we introduce a human-readable fingerprint for LLMs that uniquely identifies the base model without exposing model parameters or interfering with training. We first observe that the vector direction of LLM parameters remains stable after the model has converged during pretraining, showing negligible perturbations through subsequent training steps, including continued pretraining, supervised fine-tuning (SFT), and RLHF, which makes it a sufficient condition to identify the base model. The necessity is validated by continuing to train an LLM with an extra term to drive away the model parameters' direction and the model becomes damaged. However, this direction is vulnerable to simple attacks like dimension permutation or matrix rotation, which significantly change it without affecting performance. To address this, leveraging the Transformer structure, we systematically analyze potential attacks and define three invariant terms that identify an LLM's base model. We make these invariant terms human-readable by mapping them to a Gaussian vector using a convolutional encoder and then converting it into a natural image with StyleGAN2. Our method generates a dog image as an identity fingerprint for an LLM, where the dog's appearance strongly indicates the LLM's base model. The fingerprint provides intuitive information for qualitative discrimination, while the invariant terms can be employed for quantitative and precise verification. Experimental results across various LLMs demonstrate the effectiveness of our method.
Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that introduced by SDS. Based on the analysis, we propose a simple yet effective approach named Stable Score Distillation (SSD) which strategically orchestrates each term for high-quality 3D generation and can be readily incorporated to various 3D generation frameworks and 3D representations. Extensive experiments validate the efficacy of our approach, demonstrating its ability to generate high-fidelity 3D content without succumbing to issues such as over-smoothness.
AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.
The partial Gromov-Wasserstein (PGW) problem facilitates the comparison of measures with unequal masses residing in potentially distinct metric spaces, thereby enabling unbalanced and partial matching across these spaces. In this paper, we demonstrate that the PGW problem can be transformed into a variant of the Gromov-Wasserstein problem, akin to the conversion of the partial optimal transport problem into an optimal transport problem. This transformation leads to two new solvers, mathematically and computationally equivalent, based on the Frank-Wolfe algorithm, that provide efficient solutions to the PGW problem. We further establish that the PGW problem constitutes a metric for metric measure spaces. Finally, we validate the effectiveness of our proposed solvers in terms of computation time and performance on shape-matching and positive-unlabeled learning problems, comparing them against existing baselines.
The integration of Federated Learning (FL) and Self-supervised Learning (SSL) offers a unique and synergetic combination to exploit the audio data for general-purpose audio understanding, without compromising user data privacy. However, rare efforts have been made to investigate the SSL models in the FL regime for general-purpose audio understanding, especially when the training data is generated by large-scale heterogeneous audio sources. In this paper, we evaluate the performance of feature-matching and predictive audio-SSL techniques when integrated into large-scale FL settings simulated with non-independently identically distributed (non-iid) data. We propose a novel Federated SSL (F-SSL) framework, dubbed FASSL, that enables learning intermediate feature representations from large-scale decentralized heterogeneous clients, holding unlabelled audio data. Our study has found that audio F-SSL approaches perform on par with the centralized audio-SSL approaches on the audio-retrieval task. Extensive experiments demonstrate the effectiveness and significance of FASSL as it assists in obtaining the optimal global model for state-of-the-art FL aggregation methods.
With the advent of 5G networks and the rise of the Internet of Things (IoT), Content Delivery Networks (CDNs) are increasingly extending into the network edge. This shift introduces unique challenges, particularly due to the limited cache storage and the diverse request patterns at the edge. These edge environments can host traffic classes characterized by varied object-size distributions and object-access patterns. Such complexity makes it difficult for traditional caching strategies, which often rely on metrics like request frequency or time intervals, to be effective. Despite these complexities, the optimization of edge caching is crucial. Improved byte hit rates at the edge not only alleviate the load on the network backbone but also minimize operational costs and expedite content delivery to end-users. In this paper, we introduce HR-Cache, a comprehensive learning-based caching framework grounded in the principles of Hazard Rate (HR) ordering, a rule originally formulated to compute an upper bound on cache performance. HR-Cache leverages this rule to guide future object eviction decisions. It employs a lightweight machine learning model to learn from caching decisions made based on HR ordering, subsequently predicting the "cache-friendliness" of incoming requests. Objects deemed "cache-averse" are placed into cache as priority candidates for eviction. Through extensive experimentation, we demonstrate that HR-Cache not only consistently enhances byte hit rates compared to existing state-of-the-art methods but also achieves this with minimal prediction overhead. Our experimental results, using three real-world traces and one synthetic trace, indicate that HR-Cache consistently achieves 2.2-14.6% greater WAN traffic savings than LRU. It outperforms not only heuristic caching strategies but also the state-of-the-art learning-based algorithm.
We study how to use guidance to improve the throughput of lifelong Multi-Agent Path Finding (MAPF). Previous studies have demonstrated that while incorporating guidance, such as highways, can accelerate MAPF algorithms, this often results in a trade-off with solution quality. In addition, how to generate good guidance automatically remains largely unexplored, with current methods falling short of surpassing manually designed ones. In this work, we introduce the directed guidance graph as a versatile representation of guidance for lifelong MAPF, framing Guidance Graph Optimization (GGO) as the task of optimizing its edge weights. We present two GGO algorithms to automatically generate guidance for arbitrary lifelong MAPF algorithms and maps. The first method directly solves GGO by employing CMA-ES, a black-box optimization algorithm. The second method, PIU, optimizes an update model capable of generating guidance, demonstrating the ability to transfer optimized guidance graphs to larger maps with similar layouts. Empirically, we show that (1) our guidance graphs improve the throughput of three representative lifelong MAPF algorithms in four benchmark maps, and (2) our update model can generate guidance graphs for as large as $93 \times 91$ maps and as many as 3000 agents.
Due to strong capabilities in conducting fluent, multi-turn conversations with users, Large Language Models (LLMs) have the potential to further improve the performance of Conversational Recommender System (CRS). Unlike the aimless chit-chat that LLM excels at, CRS has a clear target. So it is imperative to control the dialogue flow in the LLM to successfully recommend appropriate items to the users. Furthermore, user feedback in CRS can assist the system in better modeling user preferences, which has been ignored by existing studies. However, simply prompting LLM to conduct conversational recommendation cannot address the above two key challenges. In this paper, we propose Multi-Agent Conversational Recommender System (MACRS) which contains two essential modules. First, we design a multi-agent act planning framework, which can control the dialogue flow based on four LLM-based agents. This cooperative multi-agent framework will generate various candidate responses based on different dialogue acts and then choose the most appropriate response as the system response, which can help MACRS plan suitable dialogue acts. Second, we propose a user feedback-aware reflection mechanism which leverages user feedback to reason errors made in previous turns to adjust the dialogue act planning, and higher-level user information from implicit semantics. We conduct extensive experiments based on user simulator to demonstrate the effectiveness of MACRS in recommendation and user preferences collection. Experimental results illustrate that MACRS demonstrates an improvement in user interaction experience compared to directly using LLMs.
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at //github.com/facebookresearch/SlowFast
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.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191