Distributional Reinforcement Learning

17 papers with code • 0 benchmarks • 0 datasets

Value distribution is the distribution of the random return received by a reinforcement learning agent. it been used for a specific purpose such as implementing risk-aware behaviour.

We have random return Z whose expectation is the value Q. This random return is also described by a recursive equation, but one of a distributional nature

Most implemented papers

Implicit Quantile Networks for Distributional Reinforcement Learning

google/dopamine ICML 2018

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN.

Distributional Reinforcement Learning with Quantile Regression

DLR-RM/stable-baselines3 27 Oct 2017

In this paper, we build on recent work advocating a distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean.

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

ku2482/fqf-iqn-qrdqn.pytorch NeurIPS 2019

The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution.

QUOTA: The Quantile Option Architecture for Reinforcement Learning

ShangtongZhang/DeepRL 5 Nov 2018

In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL).

Implicit Distributional Reinforcement Learning

zhougroup/IDAC NeurIPS 2020

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution.

Estimating Risk and Uncertainty in Deep Reinforcement Learning

IndustAI/risk-and-uncertainty 23 May 2019

Reinforcement learning agents are faced with two types of uncertainty.

GAN Q-learning

daggertye/GAN-Q-Learning 13 May 2018

Distributional reinforcement learning (distributional RL) has seen empirical success in complex Markov Decision Processes (MDPs) in the setting of nonlinear function approximation.

Information-Directed Exploration for Deep Reinforcement Learning

nikonikolov/rltf ICLR 2019

Efficient exploration remains a major challenge for reinforcement learning.

Distributional Reinforcement Learning via Moment Matching

thanhnguyentang/mmdrl 24 Jul 2020

We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-art methods that estimate the distribution, as opposed to only the expectation, of the total return.

Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment

thxsxth/POMDP_RLSepsis 21 Jan 2021

Sepsis is a potentially life threatening inflammatory response to infection or severe tissue damage.