paper-with-me

Papers

Clipped Action Policy Gradient

2018-02-21 · ICML 2018 7 · Yasuhiro Fujita, Shin-ichi Maeda

Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation. We prove that our estimator, named clipped action policy gradient (CAPG), is unbiased and achieves lower variance than the conventional estimator that ignores action bounds. Experimental results demonstrate that CAPG generally outperforms the conventional estimator, indicating that it is a better policy gradient estimator for continuous control tasks. The source code is available at https://github.com/pfnet-research/capg.

📄 PDF Abstract BibTeX arXiv:1802.07564

Code (1)

pfnet-research/capg 공식 구현

Tasks

continuous-controlContinuous ControlPolicy Gradient Methods

Similar Papers 제목 키워드 기반

Clipped-Objective Policy Gradients for Pessimistic Policy Optimization

2023-11-10 · Jared Markowitz, Edward W. Staley

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a ba…

Deep Reinforcement LearningMulti-Task LearningPolicy Gradient MethodsReinforcement Learning (RL)

The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure

2022-05-20 · Xing Chen, Dongcui Diao, Hechang Chen, Hengshuai Yao 외

The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space. Does there exist better policies outside of this space? By using a novel surrogate objective that employs the …

Efficient ExplorationPolicy Gradient Methods

KLip-PPO: A per-sample KL perspective on PPO-Clip

2026-06-22 · Riccardo Colletti, Robin Holzinger arxiv

Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning. The literature presents it in two forms, a clipped surrogate that bounds the importance ratio between suc…

Reinforcement Learning

Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications

2018-06-13 · ICLR 2019 5 · Carson Eisenach, Haichuan Yang, Ji Liu, Han Liu

Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a dis…

continuous-controlContinuous ControlReinforcement LearningReinforcement Learning (RL)

Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space

2026-03-01 · Thanh-Tuan Tran, Thanh Nguyen Canh, Nak Young Chong, Xiem HoangVan arxiv

Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. …

Reinforcement Learning