Mixed observability MDPs for shared autonomy with uncertain human behaviour

Mixed observability MDPs for shared autonomy with uncertain human behaviour

<p>Shared autonomy allows humans and AI operators to work towards a common goal. Typically, shared autonomy systems are modelled by combining a single model for human behaviour, and a model for the AI behaviour. In this paper, we attempt to provide a richer human model, which accounts for vari...

Bibliografski detalji
Glavni autori:	Costen, C, Rigter, M, Lacerda, B, Hawes, N
Format:	Conference item
Jezik:	English
Izdano:	International Joint Conferences on Artificial Intelligence Organization 2021

Slični predmeti

Planning with hidden parameter polynomial MDPs
od: Costen, C, i dr.
Izdano: (2023)

Shared autonomy systems with stochastic operator models
od: Costen, C, i dr.
Izdano: (2022)

Planning for risk-aversion and expected value in MDPs
od: Rigter, M, i dr.
Izdano: (2022)

Multi-robot allocation of assistance from a shared uncertain operator
od: Costen, C, i dr.
Izdano: (2024)

Minimax regret optimisation for robust planning in uncertain Markov decision processes
od: Rigter, M, i dr.
Izdano: (2021)

Time-bounded mission planning in time-varying domains with semi-MDPS and Gaussian processes
od: Duckworth, P, i dr.
Izdano: (2021)

Solving uncertain MDPs with objectives that are separable over instantiations of model uncertainty
od: Adulyasak, Yossiri, i dr.
Izdano: (2018)

A framework for learning from demonstration with minimal human effort
od: M Rigter, i dr.
Izdano: (2020)

Sampling Based Approaches for Minimizing Regret in Uncertain Markov Decision Processes (MDPs)
od: Ahmed, Asrar, i dr.
Izdano: (2021)

Risk-constrained planning for multi-agent systems with shared resources
od: Gautier, AL, i dr.
Izdano: (2023)

Transience in countable MDPs
od: Kiefer, SM, i dr.
Izdano: (2021)

Risk-averse Bayes-adaptive reinforcement learning
od: Rigter, M, i dr.
Izdano: (2021)

One risk to rule them all: a risk-sensitive perspective on model-based offline reinforcement learning
od: Rigter, M, i dr.
Izdano: (2024)

RAMBO-RL: robust adversarial model-based offline reinforcement learning
od: Rigter, M, i dr.
Izdano: (2023)

Long-run multi-robot planning with uncertain task durations
od: Azevedo, C, i dr.
Izdano: (2020)

Policy generation with probabilistic guarantees for long-term autonomy of a mobile robot
od: Lacerda, B, i dr.
Izdano: (2018)

Parity objectives in countable MDPs
od: Kiefer, S, i dr.
Izdano: (2017)

Büchi objectives in countable MDPs
od: Kiefer, S, i dr.
Izdano: (2019)

Multi-robot planning under uncertain travel times and safety constraints
od: Mansouri, M, i dr.
Izdano: (2019)

Social Interactions as Recursive MDPs
od: Tejwani, Ravi, i dr.
Izdano: (2022)

Mixed-initiative variable autonomy for remotely operated mobile robots
od: Chiou, M, i dr.
Izdano: (2021)

Long-run multi-robot planning under uncertain action durations for persistent tasks
od: Azevedo, C, i dr.
Izdano: (2021)

Invariant causal prediction for block MDPs
od: Zhang, A, i dr.
Izdano: (2020)

Incorporating Rich Social Interactions Into MDPs
od: Tejwani, Ravi, i dr.
Izdano: (2022)

Time-bounded planning with uncertain task duration distributions
od: Staniaszek, M, i dr.
Izdano: (2025)

Fast approximate hierarchical solution of MDPs
od: Barry, Jennifer L. (Jennifer Lynn)
Izdano: (2010)

Combining dynamic abstractions in large MDPs
od: Steinkraus, Kurt, i dr.
Izdano: (2005)

Solving Dec-MDPs with options and intention recognition
od: Cruz, Gabriel, M. Eng. Massachusetts Institute of Technology
Izdano: (2016)

Strategy complexity of parity objectives in countable MDPs
od: Kiefer, S, i dr.
Izdano: (2020)

Variable Autonomy for human-robot Teaming (VAT)
od: Chiou, Manolis, i dr.
Izdano: (2023)

NP-Hardness of checking the unichain condition in average cost MDPs
od: Tsitsiklis, John N.
Izdano: (2012)

Batch-iFDD for representation expansion in large MDPs
od: Geramifard, Alborz, i dr.
Izdano: (2015)

Adaptive Envelope MDPs for Relational Equivalence-based Planning
od: Gardiol, Natalia H., i dr.
Izdano: (2008)

Observational learning in an uncertain world
od: Acemoglu, Daron, i dr.
Izdano: (2011)

Reinforcement Learning for Mixed Autonomy Intersections
od: Yan, Zhongxia, i dr.
Izdano: (2023)

Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
od: Golowich, Noah, i dr.
Izdano: (2024)

Online plan modification in uncertain resource-constrained environments
od: Harris, CA, i dr.
Izdano: (2021)

Enabling Robotic Manipulation in Remote Environments with Shared Autonomy
od: Phung, Amy
Izdano: (2025)

A System for Human-Robot Teaming through End-User Programming and Shared Autonomy
od: Hagenow, Michael, i dr.
Izdano: (2024)

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
od: Mao, Weichao, i dr.
Izdano: (2023)