English
Related papers

Related papers: Scaling Internal-State Policy-Gradient Methods for…

200 papers

In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision…

Artificial Intelligence · Computer Science 2018-06-15 Alberto Maria Metelli , Mirco Mutti , Marcello Restelli

Optimizing a partially observable Markov decision process (POMDP) policy is challenging. The policy graph improvement (PGI) algorithm for POMDPs represents the policy as a fixed size policy graph and improves the policy monotonically. Due…

Artificial Intelligence · Computer Science 2020-09-07 Joni Pajarinen

In this paper, we propose World Model Policy Gradient (WMPG), an approach to reduce the variance of policy gradient estimates using learned world models (WM's). In WMPG, a WM is trained online and used to imagine trajectories. The imagined…

Machine Learning · Statistics 2020-10-30 Michal Nauman , Floris Den Hengst

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

With the increasing pace of automation, modern robotic systems need to act in stochastic, non-stationary, partially observable environments. A range of algorithms for finding parameterized policies that optimize for long-term average…

Machine Learning · Computer Science 2019-09-04 David Nass , Boris Belousov , Jan Peters

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

In the theory of Partially Observed Markov Decision Processes (POMDPs), existence of optimal policies have in general been established via converting the original partially observed stochastic control problem to a fully observed one on the…

Optimization and Control · Mathematics 2022-01-11 Ali Devran Kara , Serdar Yuksel

The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a Partially Observable Reinforcement Learning (PORL) problem…

Machine Learning · Computer Science 2025-10-15 Ameya Anjarlekar , Rasoul Etesami , R Srikant

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind of imitation…

Machine Learning · Computer Science 2021-07-02 Andrew Warrington , J. Wilder Lavington , Adam Ścibior , Mark Schmidt , Frank Wood

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively…

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

Machine Learning · Computer Science 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve…

Machine Learning · Computer Science 2018-06-05 Yiming Zhang , Quan Ho Vuong , Kenny Song , Xiao-Yue Gong , Keith W. Ross

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

Systems and Control · Electrical Eng. & Systems 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

In these notes we will tackle the problem of finding optimal policies for Markov decision processes (MDPs) which are not fully known to us. Our intention is to slowly transition from an offline setting to an online (learning) setting.…

Artificial Intelligence · Computer Science 2022-06-22 Guillermo A. Perez

We revisit the Reinforce policy gradient algorithm from the literature. Note that this algorithm typically works with cost returns obtained over random length episodes obtained from either termination upon reaching a goal state (as with…

Machine Learning · Computer Science 2023-10-10 Shalabh Bhatnagar

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…

Machine Learning · Computer Science 2026-05-12 Avik Kar , Siddharth Chandak , Rahul Singh , Soumitra Sinhahajari , Eric Moulines , Shalabh Bhatnagar , Nicholas Bambos

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

Machine Learning · Computer Science 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy…

Machine Learning · Computer Science 2013-01-18 Tingting Zhao , Hirotaka Hachiya , Voot Tangkaratt , Jun Morimoto , Masashi Sugiyama