Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning
Value estimation is one key problem in Reinforcement Learning. Albeit many successes have been achieved by Deep Reinforcement Learning (DRL) in different fields, the underlying structure and learning dynamics of value function, especially with complex function approximation, are not fully understood. In this paper, we report that decreasing rank of $Q$-matrix widely exists during learning process across a series of continuous control tasks for different popular algorithms. We hypothesize that the low-rank phenomenon indicates the common learning dynamics of $Q$-matrix from stochastic high dimensional space to smooth low dimensional space. Moreover, we reveal a positive correlation between value matrix rank and value estimation uncertainty. Inspired by above evidence, we propose a novel Uncertainty-Aware Low-rank Q-matrix Estimation (UA-LQE) algorithm as a general framework to facilitate the learning of value function. Through quantifying the uncertainty of state-action value estimation, we selectively erase the entries of highly uncertain values in state-action value matrix and conduct low-rank matrix reconstruction for them to recover their values. Such a reconstruction exploits the underlying structure of value matrix to improve the value approximation, thus leading to a more efficient learning process of value function. In the experiments, we evaluate the efficacy of UA-LQE in several representative OpenAI MuJoCo continuous control tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
We study matrix estimation problems arising in reinforcement learning (RL) with low-rank structure. In low-rank bandits, the matrix to be recovered specifies the expected arm rewards, and for low-rank Markov Decision Pro…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Cross-Modal Bayesian Low-Rank Adaptation for Uncertainty-Aware Multimodal Learning
Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited f…
parameter-efficient fine-tuningComputational EfficiencyAre Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty
Can a recommendation model be self-aware? This paper investigates the recommender's self-awareness by quantifying its uncertainty, which provides a label-free estimation of its performance. Such self-assessment can enabl…
Tensor-Efficient High-Dimensional Q-learning
High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-learning algorithms struggle particularly with the curse of dimensionality,…
Reinforcement LearningGroup-Aware Matrix Estimation and Latent Subspace Recovery
Modern matrix completion problems often involve heterogeneous data whose rows simultaneously belong to many meta-categories, such as demographic and age groups in recommendation systems, or region and recording session l…
Recommendation Systems