paper-with-me

Papers

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

2020-05-25 · Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry

We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO). Specifically, we investigate the consequences of "code-level optimizations:" algorithm augmentations found only in implementations or described as auxiliary details to the core algorithm. Seemingly of secondary importance, such optimizations turn out to have a major impact on agent behavior. Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO, and (b) fundamentally change how RL methods function. These insights show the difficulty and importance of attributing performance gains in deep reinforcement learning. Code for reproducing our results is available at https://github.com/MadryLab/implementation-matters .

📄 PDF Abstract BibTeX arXiv:2005.12729

Code (3)

MadryLab/implementation-matters 공식 구현 pytorch
OpenLLMAI/OpenLLaMA2 pytorch
OpenLLMAI/OpenRLHF pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…

Similar Papers 제목 키워드 기반

Implementation Matters in Deep RL: A Case Study on PPO and TRPO

2020-05-01 · ICLR 2020 1 · Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras 외

We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms, Proximal Policy Optimization and Trust Region Policy Optimization. We investigate the conseque…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Towards Understanding Deep Policy Gradients: A Case Study on PPO

2020-12-14 · CUHK Course IERG5350 2020 12 · Buhua Liu, CHONG YIN

Deep reinforcement learning has shown impressive performance on many decision-making problems, where deep policy gradient algorithms prevail in continuous action space tasks. Although many algorithm-level improvements on…

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

2020-06-10 · Marcin Andrychowicz, Anton Raichuk, Piotr Stańczyk, Manu Orsini 외

In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations t…

Attributecontinuous-controlContinuous Controlreinforcement-learning+1

What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study

2021-01-01 · ICLR 2021 1 · Marcin Andrychowicz, Anton Raichuk, Piotr Stańczyk, Manu Orsini 외

In recent years, reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numero…

Attributecontinuous-controlContinuous ControlReinforcement Learning (RL)

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

2020-07-05 · ICML 2020 1 · Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama

In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Nevertheless, UREs lead to overfitting in many p…

Weakly-supervised Learning