paper-with-me

Papers

Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces

2017-11-21 · Daniel Levy, Stefano Ermon

Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new hybrid method based on an approximation of the dynamics as an expectation over the next state under the current policy. This relaxation allows us to derive a novel hybrid policy gradient estimator, combining score function and pathwise derivative estimators, that is applicable to discrete action spaces. We show significant gains in sample complexity, ranging between $1.7$ and $25\times$, when learning parameterized policies on Cart Pole, Acrobot, Mountain Car and Hand Mass. Our method is applicable to both discrete and continuous action spaces, when competing pathwise methods are limited to the latter.

📄 PDF Abstract BibTeX arXiv:1711.08068

Code (0)

등록된 구현이 없습니다.

Tasks

AcrobotImitation Learning

Similar Papers 제목 키워드 기반

Relative Entropy Pathwise Policy Optimization

2025-07-15 · Claas Voelcker, Axel Brunnbauer, Marcel Hussing, Michal Nauman 외

Score-function policy gradients have delivered strong results in game-playing, robotics and language-model fine-tuning. Yet its high-variance often undermines training stability. On the other hand, pathwise policy gradie…

GPU

Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients

2026-05-06 · Linus Aronsson, Morteza Haghir Chehreghani arxiv

Active feature acquisition (AFA) considers prediction problems in which features are costly to obtain and the learner adaptively decides which feature values to acquire for each instance and when to stop and predict. AFA…

PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical Flowcharts

2026-05-25 · Sofiat Abioye, Ufaq Khan, Shazad Ashraf, Mohammed Adil Butt 외 arxiv

Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present …

Retry Policy Gradients in Continuous Action Spaces

2026-06-04 · Soichiro Nishimori, Paavo Parmas arxiv

Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses. In d…

Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework

2026-08-04 · Junwen Qiu, Bohao Ma, Andre Milzarek, Junyu Zhang arxiv

Unit excitation (UE) is a common assumption in stochastic saddle avoidance: the stochastic error must have a uniformly positive component along every direction, in expectation. This condition gives a direct way to rule o…

Stochastic Optimization