paper-with-me

홈 › Papers

Constrained Policy Optimization

2017-05-30 · ICML 2017 8 · Joshua Achiam, David Held, Aviv Tamar, Pieter Abbeel

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact with or around humans should satisfy safety constraints. Recent advances in policy search algorithms (Mnih et al., 2016, Schulman et al., 2015, Lillicrap et al., 2016, Levine et al., 2016) have enabled new capabilities in high-dimensional control, but do not consider the constrained setting. We propose Constrained Policy Optimization (CPO), the first general-purpose policy search algorithm for constrained reinforcement learning with guarantees for near-constraint satisfaction at each iteration. Our method allows us to train neural network policies for high-dimensional control while making guarantees about policy behavior all throughout training. Our guarantees are based on a new theoretical result, which is of independent interest: we prove a bound relating the expected returns of two policies to an average divergence between them. We demonstrate the effectiveness of our approach on simulated robot locomotion tasks where the agent must satisfy constraints motivated by safety.

📄 PDF Abstract BibTeX arXiv:1705.10528

Code (10)

Bigpig4396/PyTorch-Constrained-Policy-Optimization-CPO pytorch
awesomericky/sim2real-grounding-simulator tf
dobro12/CPO tf
ethz-asl/rl-navigation tf
hari-sikchi/pytorch_CPO pytorch
jachiam/cpo
jemaw/gym-safety
sapanachaudhary/pytorch-cpo pytorch
varunjain3/SafetyRL_HighwayEnv
ymzhang01/mujoco-circle

Tasks

Reinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Similar Papers 제목 키워드 기반

Learning to Constrain Policy Optimization with Virtual Trust Region

2022-04-20 · Hung Le, Thommen Karimpanal George, Majid Abdolshah, Dung Nguyen 외

We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using the proximity of one single old policy as …

Atari GamesPolicy Gradient Methods

First Order Constrained Optimization in Policy Space

2020-02-16 · NeurIPS 2020 12 · Yiming Zhang, Quan Vuong, Keith W. Ross

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of beha…

Reinforcement Learning

Reward Constrained Policy Optimization

2018-05-28 · ICLR 2019 5 · Chen Tessler, Daniel J. Mankowitz, Shie Mannor

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwant…

Reinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Proactive Constrained Policy Optimization with Preemptive Penalty

2025-08-03 · Ning Yang, Pengyu Wang, Guoqing Liu, Haifeng Zhang 외 arxiv

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adheren…

Reinforcement Learning

Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints

2019-11-26 · Jingliang Duan, Zhengyu Liu, Shengbo Eben Li, Qi Sun 외

This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with…