arXiv subjects

Jinyi Liu

Publications and source records attributed to Jinyi Liu.

27 records · Page 2Linked to original sources

arXiv2024

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure

Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However, MLP has obvious drawbacks. 1), The type of activation function is single and relatively fixed, which leads to poor `representation ability' of the network, and it is often to solve simple problems with complex networks; 2), the network structure is not adaptive, it is easy to cause network structure redundant or insufficient. In this work, we propose a novel neural network paradigm X-Net promising to replace MLPs. X-Net can dynamically learn activation functions individually based on derivative information during training to improve the network's representational ability for specific tasks. At the same time, X-Net can precisely adjust the network structure at the neuron level to accommodate tasks of varying complexity and reduce computational costs. We show that X-Net outperforms MLPs in terms of representational capability. X-Net can achieve comparable or even better performance than MLP with much smaller parameters on regression and classification tasks. Specifically, in terms of the number of parameters, X-Net is only 3% of MLP on average and only 1.1% under some tasks. We also demonstrate X-Net's ability to perform scientific discovery on data from various disciplines such as energy, environment, and aerospace, where X-Net is shown to help scientists discover new laws of mathematics or physics.

cs.AI↗

arXiv2024

vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement

Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL.

cs.LG↗

arXiv2024

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback

Reinforcement Learning with Human Feedback (RLHF) has received significant attention for performing tasks without the need for costly manual reward design by aligning human preferences. It is crucial to consider diverse human feedback types and various learning methods in different environments. However, quantifying progress in RLHF with diverse feedback is challenging due to the lack of standardized annotation platforms and widely used unified benchmarks. To bridge this gap, we introduce Uni-RLHF, a comprehensive system implementation tailored for RLHF. It aims to provide a complete workflow from real human feedback, fostering progress in the development of practical problems. Uni-RLHF contains three packages: 1) a universal multi-feedback annotation platform, 2) large-scale crowdsourced feedback datasets, and 3) modular offline RLHF baseline implementations. Uni-RLHF develops a user-friendly annotation interface tailored to various feedback types, compatible with a wide range of mainstream RL environments. We then establish a systematic pipeline of crowdsourced annotations, resulting in large-scale annotated datasets comprising more than 15 million steps across 30+ popular tasks. Through extensive experiments, the results in the collected datasets demonstrate competitive performance compared to those from well-designed manual rewards. We evaluate various design choices and offer insights into their strengths and potential areas of improvement. We wish to build valuable open-source platforms, datasets, and baselines to facilitate the development of more robust and reliable RLHF solutions based on realistic human feedback. The website is available at https://uni-rlhf.github.io/.

cs.LG↗

arXiv2024

Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models

Recently, there has been considerable attention towards leveraging large language models (LLMs) to enhance decision-making processes. However, aligning the natural language text instructions generated by LLMs with the vectorized operations required for execution presents a significant challenge, often necessitating task-specific details. To circumvent the need for such task-specific granularity, inspired by preference-based policy learning approaches, we investigate the utilization of multimodal LLMs to provide automated preference feedback solely from image inputs to guide decision-making. In this study, we train a multimodal LLM, termed CriticGPT, capable of understanding trajectory videos in robot manipulation tasks, serving as a critic to offer analysis and preference feedback. Subsequently, we validate the effectiveness of preference labels generated by CriticGPT from a reward modeling perspective. Experimental evaluation of the algorithm's preference accuracy demonstrates its effective generalization ability to new tasks. Furthermore, performance on Meta-World tasks reveals that CriticGPT's reward model efficiently guides policy learning, surpassing rewards based on state-of-the-art pre-trained representation models.

cs.RO↗

arXiv2023

OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments

In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we propose Optimistic Value Distribution Explorer (OVD-Explorer) to achieve a noise-aware optimistic exploration for continuous control. OVD-Explorer proposes a new measurement of the policy's exploration ability considering noise in optimistic perspectives, and leverages gradient ascent to drive exploration. Practically, OVD-Explorer can be easily integrated with continuous control RL algorithms. Extensive evaluations on the MuJoCo and GridChaos tasks demonstrate the superiority of OVD-Explorer in achieving noise-aware optimistic exploration.

cs.LG↗

arXiv2023

HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach

Offline reinforcement learning (ORL) has gained attention as a means of training reinforcement learning models using pre-collected static data. To address the issue of limited data and improve downstream ORL performance, recent work has attempted to expand the dataset's coverage through data augmentation. However, most of these methods are tied to a specific policy (policy-dependent), where the generated data can only guarantee to support the current downstream ORL policy, limiting its usage scope on other downstream policies. Moreover, the quality of synthetic data is often not well-controlled, which limits the potential for further improving the downstream policy. To tackle these issues, we propose \textbf{HI}gh-quality \textbf{PO}licy-\textbf{DE}coupled~(HIPODE), a novel data augmentation method for ORL. On the one hand, HIPODE generates high-quality synthetic data by selecting states near the dataset distribution with potentially high value among candidate states using the negative sampling technique. On the other hand, HIPODE is policy-decoupled, thus can be used as a common plug-in method for any downstream ORL process. We conduct experiments on the widely studied TD3BC and CQL algorithms, and the results show that HIPODE outperforms the state-of-the-art policy-decoupled data augmentation method and most prevalent model-based ORL methods on D4RL benchmarks.

cs.LG↗

arXiv2023

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous works focused on the pre-training in a model-free manner while lacking the study of transition dynamics modeling that leaves a large space for the improvement of sample efficiency in downstream tasks. To this end, we propose an Efficient Unsupervised Reinforcement Learning Framework with Multi-choice Dynamics model (EUCLID), which introduces a novel model-fused paradigm to jointly pre-train the dynamics model and unsupervised exploration policy in the pre-training phase, thus better leveraging the environmental samples and improving the downstream task sampling efficiency. However, constructing a generalizable model which captures the local dynamics under different behaviors remains a challenging problem. We introduce the multi-choice dynamics model that covers different local dynamics under different behaviors concurrently, which uses different heads to learn the state transition under different behaviors during unsupervised pre-training and selects the most appropriate head for prediction in the downstream task. Experimental results in the manipulation and locomotion domains demonstrate that EUCLID achieves state-of-the-art performance with high sample efficiency, basically solving the state-based URLB benchmark and reaching a mean normalized score of 104.0$\pm$1.2$\%$ in downstream tasks with 100k fine-tuning steps, which is equivalent to DDPG's performance at 2M interactive steps with 20x more data.

cs.LG↗

arXiv2023

Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain

Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomous vehicles, robotics, and so on. However, DRL and deep MARL agents are widely known to be sample inefficient that millions of interactions are usually needed even for relatively simple problem settings, thus preventing the wide application and deployment in real-industry scenarios. One bottleneck challenge behind is the well-known exploration problem, i.e., how efficiently exploring the environment and collecting informative experiences that could benefit policy learning towards the optimal ones. This problem becomes more challenging in complex environments with sparse rewards, noisy distractions, long horizons, and non-stationary co-learners. In this paper, we conduct a comprehensive survey on existing exploration methods for both single-agent and multi-agent RL. We start the survey by identifying several key challenges to efficient exploration. Beyond the above two main branches, we also include other notable exploration methods with different ideas and techniques. In addition to algorithmic analysis, we provide a comprehensive and unified empirical comparison of different exploration methods for DRL on a set of commonly used benchmarks. According to our algorithmic and empirical investigation, we finally summarize the open problems of exploration in DRL and deep MARL and point out a few future directions.

cs.AI↗

arXiv2022

Forecasts on CMB lensing observations with AliCPT-1

AliCPT-1 is the first Chinese CMB experiment aiming for high precision measurement of Cosmic Microwave Background B-mode polarization. The telescope, currently under deployment in Tibet, will observe in two frequency bands centered at 90 and 150 GHz. We forecast the CMB lensing reconstruction, lensing-galaxy as well as lensing-CIB (Cosmic Infrared Background) cross correlation signal-to-noise ratio (SNR) for AliCPT-1. We consider two stages with different integrated observation time, namely "4 module*yr" (first stage) and "48 module*yr" (final stage). For lensing reconstruction, we use three different quadratic estimators, namely temperature-only, polarization-only and minimum-variance estimators, using curved sky geometry. We take into account the impact of inhomogeneous hit counts as well as of the mean-field bias due to incomplete sky coverage. In the first stage, our results show that the 150 GHz channel is able to measure the lensing signal at $15σ$ significance with the minimum-variance estimator. In the final stage, the measurement significance will increase to $31σ$. We also combine the two frequency data in the harmonic domain to optimize the SNR. Our result show that the coadding procedure can significantly reduce the reconstruction bias in the multiple range l>800. Thanks to the high quality of the polarization data in the final stage of AliCPT-1, the EB estimator will dominate the lensing reconstruction in this stage. We also estimate the SNR of cross-correlations between AliCPT-1 CMB lensing and other tracers of the large scale structure of the universe. For its cross-correlation with DESI galaxies/quasars, we report the cross-correlation SNR = 10-20 for the 4 redshift bins at 0.05<z<2.1. In the first stage, the total SNR is about $32$. In the final stage, the lensing-galaxy cross-correlation can reach SNR=52.

astro-ph.CO↗