AI Chat AI Image Generator AI Video Text to Speech

Reinforcement Learning in Non-Markovian Environments

11/03/2022

∙

by Siddharth Chandak, et al.

∙

∙

Following the novel paradigm developed by Van Roy and coauthors for reinforcement learning in arbitrary non-Markovian environments, we propose a related formulation inspired by classical stochastic control that reduces the problem to recursive computation of approximate sufficient statistics.

Siddharth Chandak
6 publications
Vivek S. Borkar
13 publications
Parth Dodhia
1 publication

page 1

page 2

page 3

page 4

research

∙ 01/27/2020

Some Insights into Lifelong Reinforcement Learning Systems

A lifelong reinforcement learning system is a learning system that has t...

0 Changjian Li, et al. ∙

research

∙ 06/14/2022

Robust Reinforcement Learning with Distributional Risk-averse formulation

Robust Reinforcement Learning tries to make predictions more robust to c...

0 Pierre Clavier, et al. ∙

research

∙ 02/11/2021

Echo State Networks for Reinforcement Learning

Echo State Networks (ESNs) are a type of single-layer recurrent neural n...

0 Allen G Hart, et al. ∙

research

∙ 03/27/2013

ABC Reinforcement Learning

This paper introduces a simple, general framework for likelihood-free Ba...

0 Christos Dimitrakakis, et al. ∙

research

∙ 07/30/2019

Wasserstein Robust Reinforcement Learning

Reinforcement learning algorithms, though successful, tend to over-fit t...

2 Mohammed Amin Abdullah, et al. ∙

research

∙ 08/07/2023

Deep Q-Network for Stochastic Process Environments

Reinforcement learning is a powerful approach for training an optimal po...

0 Kuangheng He, et al. ∙

research

∙ 06/25/2018

A Tour of Reinforcement Learning: The View from Continuous Control

This manuscript surveys reinforcement learning from the perspective of o...

14 Benjamin Recht, et al. ∙