Browse SoTA > Methodology > Distributional Reinforcement Learning

Distributional Reinforcement Learning

9 papers with code · Methodology

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Implicit Quantile Networks for Distributional Reinforcement Learning

ICML 2018 google/dopamine

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.

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

Distributional Reinforcement Learning with Quantile Regression

27 Oct 2017facebookresearch/ReAgent

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.

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

QUOTA: The Quantile Option Architecture for Reinforcement Learning

5 Nov 2018ShangtongZhang/DeepRL

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

DECISION MAKING DISTRIBUTIONAL REINFORCEMENT LEARNING

GAN Q-learning

13 May 2018daggertye/GAN-Q-Learning

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

DISTRIBUTIONAL REINFORCEMENT LEARNING OPENAI GYM Q-LEARNING

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

NeurIPS 2019 ku2482/fqf-iqn-qrdqn.pytorch

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

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

NeurIPS 2019 ku2482/fqf-iqn-qrdqn.pytorch

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

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

Estimating Risk and Uncertainty in Deep Reinforcement Learning

23 May 2019uncharted-technologies/risk-and-uncertainty

Our method combines elements from distributional reinforcement learning and approximate Bayesian inference techniques with neural networks, allowing us to disentangle both types of uncertainty on the expected return of a policy.

BAYESIAN INFERENCE DISTRIBUTIONAL REINFORCEMENT LEARNING EFFICIENT EXPLORATION

Distributional Reinforcement Learning with Maximum Mean Discrepancy

24 Jul 2020thanhnguyentang/mmdrl

Distributional reinforcement learning (RL) has achieved state-of-the-art performance in Atari games by recasting the traditional RL into a distribution estimation problem, explicitly estimating the probability distribution instead of the expectation of a total return.

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING