Related papers: SQT -- std $Q$-target
The compensated quotient-difference (Compqd) algorithm is proposed along with some applications. The main motivation is based on the fact that the standard quotient-difference (qd) algorithm can be numerically unstable. The Compqd algorithm…
Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…
In this paper, we delve into the statistical analysis of the fitted Q-evaluation (FQE) method, which focuses on estimating the value of a target policy using offline data generated by some behavior policy. We provide a comprehensive…
This paper presents a novel and comprehensive solution to enhance both the robustness and efficiency of question answering (QA) systems through supervised contrastive learning (SCL). Training a high-performance QA system has become…
Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression…
The Sampled Policy Gradient (SPG) algorithm is a new offline actor-critic variant that samples in the action space to approximate the policy gradient. It does so by using the critic to evaluate the sampled actions. SPG offers theoretical…
We present $\Delta$-UQ -- a novel, general-purpose uncertainty estimator using the concept of anchoring in predictive models. Anchoring works by first transforming the input into a tuple consisting of an anchor point drawn from a prior…
Quantized networks use less computational and memory resources and are suitable for deployment on edge devices. While quantization-aware training QAT is the well-studied approach to quantize the networks at low precision, most research…
Instability and variability of Deep Reinforcement Learning (DRL) algorithms tend to adversely affect their performance. Averaged-DQN is a simple extension to the DQN algorithm, based on averaging previously learned Q-values estimates, which…
Real-time quantum error correction places the classical decoder inside the fault-tolerant control loop under strict timing and memory constraints. For quantum low-density parity-check (QLDPC) codes, practical deployment therefore depends…
In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can…
A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior…
In this work, we build upon the offline reinforcement learning algorithm TD7, which incorporates State-Action Learned Embeddings (SALE) and a prioritized experience replay buffer (LAP). We propose a model-free actor-critic algorithm that…
We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on…
Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use of on-policy data. We propose a framework to bridge this…
In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully employed for compressing large language models (LLMs) due to…
We propose a new Q-learning variant, called 2RA Q-learning, that addresses some weaknesses of existing Q-learning methods in a principled manner. One such weakness is an underlying estimation bias which cannot be controlled and often…
Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with…
Greedy-GQ with linear function approximation, originally proposed in \cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with the…