相关论文: Deep Reinforcement Learning with Importance Weight…

Deep reinforcement learning (DRL) has great potential for acquiring the optimal action in complex environments such as games and robot control. However, it is difficult to analyze the decision-making of the agent, i.e., the reasons it…

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency…

Adaptive bitrate (ABR) streaming is the de facto solution for achieving smooth viewing experiences under unstable network conditions. However, most of the existing rate adaptation approaches for ABR are content-agnostic, without considering…

As an important algorithm in deep reinforcement learning, advantage actor critic (A2C) has been widely succeeded in both discrete and continuous control tasks with raw pixel inputs, but its sample efficiency still needs to improve more. In…

Traditional ETF stock selection methods and reinforcement learning models such as the Asynchronous Advantage Actor-Critic (A3C) often suffer from high-dimensional feature spaces and overfitting when applied to complex financial markets.…

As cloud computing and microservice architectures become increasingly prevalent, API rate limiting has emerged as a critical mechanism for ensuring system stability and service quality. Traditional rate limiting algorithms, such as token…

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it…

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empowered by natural language understanding and traditional…

Low-Rank Adaptation (LoRA) is the bread and butter of Large Language Model (LLM) finetuning. LoRA learns an additive low-rank perturbation, $AB$, of a pretrained matrix parameter $W$ to align the model to a new task or dataset with $W+AB$.…

This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient…

This work is an exploratory research concerned with determining in what way reinforcement learning can be used to predict optimal PID parameters for a robot designed for apple harvest. To study this, an algorithm called Advantage Actor…

In today's Internet, HTTP Adaptive Streaming (HAS) is the mainstream standard for video streaming, which switches the bitrate of the video content based on an Adaptive BitRate (ABR) algorithm. An effective Quality of Experience (QoE)…

Reinforcement learning (RL) for large language models (LLMs) is dominated by the cost of rollout generation, which has motivated the use of low-precision rollouts (e.g., FP8) paired with a BF16 trainer to improve throughput and reduce…

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost…

The enhanced distributed channel access (EDCA) mechanism is used in current wireless fidelity (WiFi) networks to support priority requirements of heterogeneous applications. However, the EDCA mechanism can not adapt to particular…

Existing reinforcement learning~(RL)-based adaptive bitrate~(ABR) approaches outperform the previous fixed control rules based methods by improving the Quality of Experience~(QoE) score, as the QoE metric can hardly provide clear guidance…

Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collected online experiences. Standard methods, often relying on a fixed data-mixing ratio, struggle to…

Adaptive Bitrate (ABR) Streaming over the cellular networks has been well studied in the literature; however, existing ABR algorithms primarily focus on improving the end-users' Quality of Experience (QoE) while ignoring the resource…

While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the…