Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

223446669892 · Jun 202019922001200920172026
48 results for partially observable Markov decision processes

We characterize value functions in partially observable MDPs as semi-algebraic sets.

problem Understanding feasible value functions in partially observable Markov decision processes.
method Characterization of feasible value functions as semi-algebraic sets defined by polynomial inequalities.
result The feasible set of value functions in POMDPs is a semi-algebraic set, not a polytope as in MDPs.

A new algorithm trains experts to safely guide agents in partially observed environments.

problem Existing imitation learning methods for POMDPs can lead to sub-optimal or unsafe policies.
method Derive an objective to encourage the expert to maximize the agent's reward, then use it to train both expert and agent.
result The algorithm produces an expert policy that the agent can safely imitate, outperforming fixed expert policies.

New algorithm improves reinforcement learning from partial observations.

problem Inferior performance of algorithms in real-world reinforcement learning due to partial observability.
method Representation-based approach to POMDPs, leading to a tractable algorithm.
result Empirically demonstrates superior performance with partial observations.

We solve a broad class of sequential decision-making problems with partially observed states.

problem Sequential decision-making under uncertainty with partially observed states.
method Modeling as a partially observed Markov decision process (POMDP) and separating state and modulation process.
result The approach allows for specialized approximate solution procedures.

Paper analyzes history-based RL methods for MDPs, introduces a theoretical framework and practical algorithm.

problem Improving RL performance in MDPs using history-based features.
method Theoretical framework for history-based RL, practical algorithm design.
result Practical RL algorithm shows effectiveness on continuous control tasks.

A new metric detects non-Markovian states in partially observable environments.

problem Learning state representations in partially observable environments.
method Introducing the λλ-discrepancy metric to detect non-Markovian states.
result The λλ-discrepancy is zero for Markov processes and non-zero for partially observable environments.

New algorithms learn POMDPs efficiently with hindsight observability.

problem Hardness of learning in POMDPs due to partial observability.
method Hindsight Observable Markov Decision Process (HOMDP) and new algorithms for tabular and function approximation settings.
result Sample-efficient learning in POMDPs with optimal dependence on latent state and observation cardinalities.

PRL improves off-policy evaluation in partially observed MDPs.

problem Confounding and bias in offline reinforcement learning with unobserved state factors.
method Extends proximal causal inference to POMDPs, identifying and estimating target policy value.
result Semiparametrically efficient estimators for PRL in partially observed MDPs.

New method for evaluating policies in complex decision-making models with hidden variables.

problem Evaluating policies in partially observable Markov decision processes with hidden confounders.
method Introduces novel identification methods and minimax estimation techniques for linking target policy's value and observed data distribution.
result Proposes three estimators for off-policy evaluation in POMDPs with latent confounders, demonstrating their effectiveness through nonasymptotic and asymptotic analysis.

Study optimal policy regret in partially observable Markov games with adaptive opponents.

problem Optimal sequential decision-making in partially observable environments against strategic, adaptive opponents.
method An epoch-based optimistic maximum-likelihood algorithm that selects one policy per epoch using confidence sets built cumulatively from past data.
result Achieves ildeO(T) ilde{O}(\sqrt{T}) policy regret for fixed problem parameters, with explicit dependence on horizon, adversary memory, confidence radius, and aggregate Eluder dimension.

New algorithm tackles confounding in offline RL for partially observable MDPs.

problem Confounding in offline reinforcement learning for partially observable MDPs.
method P3O algorithm using proximal causal inference and pessimistic confidence regions.
result Achieves n1/2n^{-1/2}-suboptimality for offline RL in POMDPs with confounded data.

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…

2019-09-09abs ↗pdf ↗

This paper is concerned with multi-view reinforcement learning (MVRL), which allows for decision making when agents share common dynamics but adhere to different observation models. We define the MVRL framework by extending partially observable Markov decision processes (POMDPs) to support more than one observation mod…

2019-10-18abs ↗pdf ↗

Study evaluates policies in partially observable environments without full model specification.

problem Evaluating policies in partially observable environments without full model specification.
method Developed non-parametric identification and recursive fitted-Q-evaluation algorithm.
result Established finite-sample error bounds for policy value estimation.

Paper solves POMDPs in continuous time and discrete spaces.

problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.

Enhances RL in partially observable, noisy environments by uncovering causal states.

problem Making decisions based on incomplete and noisy observations in partially observable Markov decision processes (P2^2OMDPs).
method Causal State Representation under Asynchronous Diffusion Model (CaDiff) framework, incorporating a novel asynchronous diffusion model (ADM) and a new bisimulation metric.
result Enhances returns by at least 14.18% compared to baselines on Roboschool tasks.

New method for robust policy evaluation in offline reinforcement learning with sequentially exogenous unobserved confounders.

problem Offline reinforcement learning in domains with unobserved confounders.
method Orthogonalized robust fitted-Q-iteration with closed-form solutions and bias-correction.
result Effective in simulations and real-world data, improving robustness and computational ease.

Study uses multi-agent reinforcement learning to control self-assembly with high-resolution external control.

problem Designing effective external control protocols for self-assembly with high-resolution control.
method Investigated a multi-agent reinforcement learning approach, comparing fully decentralized and partially decentralized strategies.
result Partially decentralized approach outperforms fully decentralized in controlling self-assembly towards target structures.

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…

2012-12-12abs ↗pdf ↗

Efficient RL in partially observable risk-sensitive environments with hindsight observations.

problem Risk-sensitive reinforcement learning in partially observable environments.
method Integrates hindsight observations into POMDP framework, develops novel RL algorithm.
result Achieves polynomial regret with provable efficiency, outperforming existing methods.

We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conduct…

2016-02-08abs ↗pdf ↗

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging…

2016-02-25abs ↗pdf ↗

We study a multi-armed bandit problem where the rewards exhibit regime switching. Specifically, the distributions of the random rewards generated from all arms are modulated by a common underlying state modeled as a finite-state Markov chain. The agent does not observe the underlying state and has to learn the transiti…

2020-01-26abs ↗pdf ↗

RL struggles with generalization due to implicit partial observability.

problem Generalization in RL is difficult due to implicit partial observability.
method Re-cast RL problem as solving epistemic POMDPs and propose ensemble-based techniques.
result Simple ensemble-based technique achieves significant generalization gains.

This paper establishes strong lower bounds for learning in revealing POMDPs.

problem Understanding the fundamental limits of reinforcement learning in revealing partially observable Markov Decision Processes (POMDPs).
method Develops strong PAC and regret lower bounds for learning in revealing POMDPs using multi-step revealing POMDPs as a case study.
result Strong polynomial lower bounds for learning in revealing POMDPs, achieving significantly smaller gaps against current upper bounds.

RL agents fail to generalize to unseen environments, even when dynamics are similar.

problem RL agents fail to generalize to unseen environments despite similar dynamics.
method Analyzed policy learning in POMDPs, formalized training dynamics as instances, and introduced a shared belief representation over an ensemble of specialized policies.
result Maximizing rewards induces instance-specific policies that are suboptimal on the training set.

New algorithms solve robust MDPs efficiently, significantly faster than existing methods.

problem Computing robust MDP solutions with uncertainty in transition probabilities is computationally expensive.
method Partial policy iteration and fast robust Bellman operator computation methods.
result The proposed methods are many orders of magnitude faster than state-of-the-art approaches.