Related papers: Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection

Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection

URL: http://arxiv.org/abs/2105.09452v1
Date: Thu, 20 May 2021 01:57:52 GMT
Title: Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection
Authors: Lucas N. Alegre, Ana L. C. Bazzan, Bruno C. da Silva
Abstract summary: We introduce an algorithm that efficiently learns policies in non-stationary environments. It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detection statistics. We show that (i) this algorithm minimizes the delay until unforeseen changes to a context are detected, thereby allowing for rapid responses.
Score: 7.685002911021767
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes performance over a possibly infinite random sequence of Markov Decision Processes (MDPs), each of which drawn from some unknown distribution. We call each such MDP a context. Most related works make strong assumptions such as knowledge about the distribution over contexts, the existence of pre-training phases, or a priori knowledge about the number, sequence, or boundaries between contexts. We introduce an algorithm that efficiently learns policies in non-stationary environments. It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detection statistics that reflect whether novel, specialized policies need to be created and deployed to tackle novel contexts, or whether previously-optimized ones might be reused. We show that (i) this algorithm minimizes the delay until unforeseen changes to a context are detected, thereby allowing for rapid responses; and (ii) it bounds the rate of false alarm, which is important in order to minimize regret. Our method constructs a mixture model composed of a (possibly infinite) ensemble of probabilistic dynamics predictors that model the different modes of the distribution over underlying latent MDPs. We evaluate our algorithm on high-dimensional continuous reinforcement learning problems and show that it outperforms state-of-the-art (model-free and model-based) RL algorithms, as well as state-of-the-art meta-learning methods specially designed to deal with non-stationarity.

Related papers

Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes [7.028778922533688]
Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. We study a unique structural property of average-reward MDPs and utilize it to introduce Reward-Extended Differential (or RED) reinforcement learning.
arXiv Detail & Related papers (2024-10-14T14:52:23Z)
Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [94.2860766709971]
We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a wireless network with statistically-identical agents. Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies.
arXiv Detail & Related papers (2024-04-04T06:24:11Z)
Fast Value Tracking for Deep Reinforcement Learning [7.648784748888187]
Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interact with their environment. Existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards. Our research leverages the Kalman paradigm to introduce a novel quantification and sampling algorithm called Langevinized Kalman TemporalTD.
arXiv Detail & Related papers (2024-03-19T22:18:19Z)
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
arXiv Detail & Related papers (2023-07-01T18:35:21Z)
Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
arXiv Detail & Related papers (2022-09-15T07:22:58Z)
Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning [0.0]
offline estimation of the dynamical model of a Markov Decision Process (MDP) is a non-trivial task. Recent works showed that an expert-guided pipeline relying on Density Estimation methods effectively detects this structure in deterministic environments. We show that the former results lead to a performance improvement when solving the learned MDP and then applying the optimized policy in the real environment.
arXiv Detail & Related papers (2021-12-18T14:32:32Z)
Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms. We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework. Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
arXiv Detail & Related papers (2020-06-18T19:04:09Z)
Optimizing for the Future in Non-Stationary MDPs [52.373873622008944]
We present a policy gradient algorithm that maximizes a forecast of future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques.
arXiv Detail & Related papers (2020-05-17T03:41:19Z)
Study of Diffusion Normalized Least Mean M-estimate Algorithms [0.8749675983608171]
This work proposes diffusion normalized least mean M-estimate algorithm based on the modified Huber function. We analyze the transient, steady-state and stability behaviors of the algorithms in a unified framework. Simulations in various impulsive noise scenarios show that the proposed algorithms are superior to some existing diffusion algorithms.
arXiv Detail & Related papers (2020-04-20T00:28:41Z)
Dynamic Federated Learning [57.14673504239551]
Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
arXiv Detail & Related papers (2020-02-20T15:00:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.