Distributional Reinforcement Learning

26 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

opendilab/DI-engine 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 for Energy-Based Sequential Models

parshakova/GAMS-for-Data-Efficient-Learning 18 Dec 2019

Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models.

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.