paper-with-me

Papers

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 behavior-such as ones which are deemed unsafe and to be avoided-are best captured through constraints. We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent's overall reward while ensuring the agent satisfies a set of cost constraints. Using data generated from the current policy, FOCOPS first finds the optimal update policy by solving a constrained optimization problem in the nonparameterized policy space. FOCOPS then projects the update policy back into the parametric policy space. Our approach has an approximate upper bound for worst-case constraint violation throughout training and is first-order in nature therefore simple to implement. We provide empirical evidence that our simple approach achieves better performance on a set of constrained robotics locomotive tasks.

📄 PDF Abstract BibTeX arXiv:2002.06506

Code (2)

ymzhang01/focops 공식 구현 pytorch
hmhuy0/SIM-RL pytorch

Tasks

Reinforcement Learning

Methods 이 논문이 사용한 방법론

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…
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…

Similar Papers 제목 키워드 기반

Multi-Agent First Order Constrained Optimization in Policy Space

2023-09-21 · NeurIPS 2023 11

In the realm of multi-agent reinforcement learning (MARL), achieving high performance is crucial for a successful multi-agent system. Meanwhile, the ability to avoid unsafe actions is becoming an urgent and imperative pr…

Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning

2025-07-06 · Uri Sherman, Tomer Koren, Yishay Mansour arxiv

We study reinforcement learning (RL) in the agnostic policy learning setting, where the goal is to find a policy whose performance is competitive with the best policy in a given class of interest $Π$ -- crucially, withou…

Reinforcement Learning

Constrained Proximal Policy Optimization

2023-05-23 · Chengbin Xuan, Feng Zhang, Faliang Yin, Hak-Keung Lam

The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, w…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

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)

FlowPG: Action-constrained Policy Gradient with Normalizing Flows

2024-02-07 · NeurIPS 2023 11 · Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid act…

continuous-controlContinuous ControlDecision Makingvalid