paper-with-me

Papers

Differentiable Trust Region Layers for Deep Reinforcement Learning

2021-01-22 · ICLR 2021 1 · Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche, Gerhard Neumann

Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is difficult. Hence, many approaches, such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), are based on approximations. Due to those approximations, they violate the constraints or fail to find the optimal solution within the trust region. Moreover, they are difficult to implement, often lack sufficient exploration, and have been shown to depend on seemingly unrelated implementation choices. In this work, we propose differentiable neural network layers to enforce trust regions for deep Gaussian policies via closed-form projections. Unlike existing methods, those layers formalize trust regions for each state individually and can complement existing reinforcement learning algorithms. We derive trust region projections based on the Kullback-Leibler divergence, the Wasserstein L2 distance, and the Frobenius norm for Gaussian distributions. We empirically demonstrate that those projection layers achieve similar or better results than existing methods while being almost agnostic to specific implementation choices. The code is available at https://git.io/Jthb0.

📄 PDF Abstract BibTeX arXiv:2101.09207

Code (1)

boschresearch/trust-region-layers 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Deep Black-Box Reinforcement Learning with Movement Primitives

2022-10-18 · Fabian Otto, Onur Celik, Hongyi Zhou, Hanna Ziesche 외

\Episode-based reinforcement learning (ERL) algorithms treat reinforcement learning (RL) as a black-box optimization problem where we learn to select a parameter vector of a controller, often represented as a movement pr…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

TROLL: Trust Regions improve Reinforcement Learning for Large Language Models

2025-10-04 · Philipp Becker, Niklas Freymuth, Serge Thilges, Fabian Otto 외 arxiv

Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has explored improved estimators of advantages a…

Reinforcement LearningMathematical ReasoningCode Generation

TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning

2023-12-01 · Dohyeong Kim, Songhwai Oh

As safety is of paramount importance in robotics, reinforcement learning that reflects safety, called safe RL, has been studied extensively. In safe RL, we aim to find a policy which maximizes the desired return while sa…

reinforcement-learningSafe Reinforcement Learning

Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks

2026-01-29 · Jinhao Li, Yuhao Sun, Zhiyuan Ma, Hao He 외 arxiv

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based…

Reinforcement Learning

Quasi-Newton Trust Region Policy Optimization

2019-12-26 · Devesh Jha, Arvind Raghunathan, Diego Romeres

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm fo…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1