paper-with-me

Papers

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

2022-02-06 · Michael Teng, Michiel Van de Panne, Frank Wood

Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based critic. This approach has been successfully integrated into common RL methods for continuous control, giving rise to algorithms such as Distributional Soft Actor-Critic (DSAC). In this paper, we introduce multi-sample target values (MTV) for distributional RL, as a principled replacement for single-sample target value estimation, as commonly employed in current practice. The improved distributional estimates further lend themselves to UCB-based exploration. These two ideas are combined to yield our distributional RL algorithm, E2DC (Extra Exploration with Distributional Critics). We evaluate our approach on a range of continuous control tasks and demonstrate state-of-the-art model-free performance on difficult tasks such as Humanoid control. We provide further insight into the method via visualization and analysis of the learned distributions and their evolution during training.

📄 PDF Abstract BibTeX arXiv:2202.02693

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlDistributional Reinforcement LearningHumanoid Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration

2024-10-25 · Hai Zhong, Xun Wang, Zhuoran Li, Longbo Huang

Offline-to-Online Reinforcement Learning has emerged as a powerful paradigm, leveraging offline data for initialization and online fine-tuning to enhance both sample efficiency and performance. However, most existing res…

Efficient ExplorationMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+3

Post-Selection Distributional Model Evaluation

2026-03-24 · Amirmohammad Farzaneh, Osvaldo Simeone arxiv

Formal model evaluation methods typically certify that a model satisfies a prescribed target key performance indicator (KPI) level. However, in many applications, the relevant target KPI level may not be known a priori, …

Worst-Case Analysis for Randomly Collected Data

2019-11-09 · NeurIPS 2020 12 · Justin Y. Chen, Gregory Valiant, Paul Valiant

We introduce a framework for statistical estimation that leverages knowledge of how samples are collected but makes no distributional assumptions on the data values. Specifically, we consider a population of elements $[n…

Bayesian Distributional Policy Gradients

2021-03-20 · Luchen Li, A. Aldo Faisal

Distributional Reinforcement Learning (RL) maintains the entire probability distribution of the reward-to-go, i.e. the return, providing more learning signals that account for the uncertainty associated with policy perfo…

Atari GamesContrastive LearningDistributional Reinforcement LearningMuJoCo+1

Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN

2018-08-06 · Dror Freirich, Ron Meir, Aviv Tamar

The recently proposed distributional approach to reinforcement learning (DiRL) is centered on learning the distribution of the reward-to-go, often referred to as the value distribution. In this work, we show that the dis…

Generative Adversarial NetworkReinforcement Learning