Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands. Even in simulation with no sample constraints, scripting controllers is intractable due to high degrees of freedom, and manual reward engineering can also be hard and lead to non-realistic motions. Leveraging the recent progress on Reinforcement Learning from Human Feedback (RLHF), we propose a framework to learn a universal human prior using direct human preference feedback over videos, for efficiently tuning the RL policy on 20 dual-hand robot manipulation tasks in simulation, without a single human demonstration. One task-agnostic reward model is trained through iteratively generating diverse polices and collecting human preference over the trajectories; it is then applied for regularizing the behavior of polices in the fine-tuning stage. Our method empirically demonstrates more human-like behaviors on robot hands in diverse tasks including even unseen tasks, indicating its generalization capability.
相關內容
Large language models (LLMs) have recently received significant attention for their exceptional capabilities. Despite extensive efforts in developing general-purpose LLMs that can be utilized in various natural language processing (NLP) tasks, there has been less research exploring their potential in recommender systems. In this paper, we propose a novel framework, named PALR, which aiming to combine user history behaviors (such as clicks, purchases, ratings, etc.) with LLMs to generate user preferred items. Specifically, we first use user/item interactions as guidance for candidate retrieval. Then we adopt a LLM-based ranking model to generate recommended items. Unlike existing approaches that typically adopt general-purpose LLMs for zero/few-shot recommendation testing or training on small-sized language models (with less than 1 billion parameters), which cannot fully elicit LLMs' reasoning abilities and leverage rich item side parametric knowledge, we fine-tune a 7 billion parameters LLM for the ranking purpose. This model takes retrieval candidates in natural language format as input, with instruction which explicitly asking to select results from input candidates during inference. Our experimental results demonstrate that our solution outperforms state-of-the-art models on various sequential recommendation tasks.
This paper tackles text-guided control of StyleGAN for editing garments in full-body human images. Existing StyleGAN-based methods suffer from handling the rich diversity of garments and body shapes and poses. We propose a framework for text-guided full-body human image synthesis via an attention-based latent code mapper, which enables more disentangled control of StyleGAN than existing mappers. Our latent code mapper adopts an attention mechanism that adaptively manipulates individual latent codes on different StyleGAN layers under text guidance. In addition, we introduce feature-space masking at inference time to avoid unwanted changes caused by text inputs. Our quantitative and qualitative evaluations reveal that our method can control generated images more faithfully to given texts than existing methods.
Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Behavior estimation aims at estimating the policy with which training data are generated. In particular, this work considers a scenario where the data are collected from multiple sources. In this case, neglecting data heterogeneity, existing approaches for behavior estimation suffers from behavior misspecification. To overcome this drawback, the present study proposes a latent variable model to infer a set of policies from data, which allows an agent to use as behavior policy the policy that best describes a particular trajectory. This model provides with a agent fine-grained characterization for multi-source data and helps it overcome behavior misspecification. This work also proposes a learning algorithm for this model and illustrates its practical usage via extending an existing offline RL algorithm. Lastly, with extensive evaluation this work confirms the existence of behavior misspecification and the efficacy of the proposed model.
We study the fundamental mistake bound and sample complexity in the strategic classification, where agents can strategically manipulate their feature vector up to an extent in order to be predicted as positive. For example, given a classifier determining college admission, student candidates may try to take easier classes to improve their GPA, retake SAT and change schools in an effort to fool the classifier. Ball manipulations are a widely studied class of manipulations in the literature, where agents can modify their feature vector within a bounded radius ball. Unlike most prior work, our work considers manipulations to be personalized, meaning that agents can have different levels of manipulation abilities (e.g., varying radii for ball manipulations), and unknown to the learner. We formalize the learning problem in an interaction model where the learner first deploys a classifier and the agent manipulates the feature vector within their manipulation set to game the deployed classifier. We investigate various scenarios in terms of the information available to the learner during the interaction, such as observing the original feature vector before or after deployment, observing the manipulated feature vector, or not seeing either the original or the manipulated feature vector. We begin by providing online mistake bounds and PAC sample complexity in these scenarios for ball manipulations. We also explore non-ball manipulations and show that, even in the simplest scenario where both the original and the manipulated feature vectors are revealed, the mistake bounds and sample complexity are lower bounded by $\Omega(|\mathcal{H}|)$ when the target function belongs to a known class $\mathcal{H}$.
Automated planning is concerned with developing efficient algorithms to generate plans or sequences of actions to achieve a specific goal in a given environment. Emerging Large Language Models (LLMs) can answer questions, write high-quality programming code, and predict protein folding, showcasing their versatility in solving various tasks beyond language-based problems. In this paper, we aim to explore how LLMs can also be used for automated planning. To do so, we seek to answer four key questions. Firstly, we want to understand the extent to which LLMs can be used for plan generation. Secondly, we aim to identify which pre-training data is most effective in facilitating plan generation. Thirdly, we investigate whether fine-tuning or prompting is a more effective approach for plan generation. Finally, we explore whether LLMs are capable of plan generalization. By answering these questions, the study seeks to shed light on the capabilities of LLMs in solving complex planning problems and provide insights into the most effective approaches for using LLMs in this context.
Machine-readable representations of privacy policies are door openers for a broad variety of novel privacy-enhancing and, in particular, transparency-enhancing technologies (TETs). In order to generate such representations, transparency information needs to be extracted from written privacy policies. However, respective manual annotation and extraction processes are laborious and require expert knowledge. Approaches for fully automated annotation, in turn, have so far not succeeded due to overly high error rates in the specific domain of privacy policies. In the end, a lack of properly annotated privacy policies and respective machine-readable representations persists and enduringly hinders the development and establishment of novel technical approaches fostering policy perception and data subject informedness. In this work, we present a prototype system for a `Human-in-the-Loop' approach to privacy policy annotation that integrates ML-generated suggestions and ultimately human annotation decisions. We propose an ML-based suggestion system specifically tailored to the constraint of data scarcity prevalent in the domain of privacy policy annotation. On this basis, we provide meaningful predictions to users thereby streamlining the annotation process. Additionally, we also evaluate our approach through a prototypical implementation to show that our ML-based extraction approach provides superior performance over other recently used extraction models for legal documents.
Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.
The potential of graph convolutional neural networks for the task of zero-shot learning has been demonstrated recently. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, knowledge from distant nodes can get diluted when propagating through intermediate nodes, because current approaches to zero-shot learning use graph propagation schemes that perform Laplacian smoothing at each layer. We show that extensive smoothing does not help the task of regressing classifier weights in zero-shot learning. In order to still incorporate information from distant nodes and utilize the graph structure, we propose an Attentive Dense Graph Propagation Module (ADGPM). ADGPM allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node's relationship to its ancestors and descendants and an attention scheme is further used to weigh their contribution depending on the distance to the node. Finally, we illustrate that finetuning of the feature representation after training the ADGPM leads to considerable improvements. Our method achieves competitive results, outperforming previous zero-shot learning approaches.
Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191