Towards Characterizing Divergence in Deep Q-Learning
Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation. Prior work has demonstrated that together these can lead to divergence in Q-learning algorithms, but the conditions under which divergence occurs are not well-understood. In this note, we give a simple analysis based on a linear approximation to the Q-value updates, which we believe provides insight into divergence under the deadly triad. The central point in our analysis is to consider when the leading order approximation to the deep-Q update is or is not a contraction in the sup norm. Based on this analysis, we develop an algorithm which permits stable deep Q-learning for continuous control without any of the tricks conventionally used (such as target networks, adaptive gradient optimizers, or using multiple Q functions). We demonstrate that our algorithm performs above or near state-of-the-art on standard MuJoCo benchmarks from the OpenAI Gym.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlMuJoCoOpenAI GymQ-LearningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Estimating $L_2^2$ Divergence
We give a comprehensive theoretical characterization of a nonparametric estimator for the $L_2^2$ divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it …
A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie th…
Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences
Data-processing is a desired property of classical and quantum divergences and information measures. In information theory, the contraction coefficient measures how much the distinguishability of quantum states decreases…
Measured Hockey-Stick Divergence and its Applications to Quantum Pufferfish Privacy
The hockey-stick divergence is a fundamental quantity characterizing several statistical privacy frameworks that ensure privacy for classical and quantum data. In such quantum privacy frameworks, the adversary is allowed…
Regularization via f-Divergence: An Application to Multi-Oxide Spectroscopic Analysis
In this paper, we address the task of characterizing the chemical composition of planetary surfaces using convolutional neural networks (CNNs). Specifically, we seek to predict the multi-oxide weights of rock samples bas…
Multi-target regression