Invariant causal prediction for block MDPs

Invariant causal prediction for block MDPs

Generalization across environments is critical to the successful application of reinforcement learning (RL) algorithms to real-world challenges. In this work we propose a method for learning state abstractions which generalize to novel observation distributions in the multi-environment RL setting. W...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron:	Zhang, A, Lyle, C, Sodhani, S, Filos, A, Kwiatkowska, M, Pineau, J, Gal, Y, Precup, D
Fformat:	Conference item
Iaith:	English
Cyhoeddwyd:	Proceedings of Machine Learning Research 2020

Eitemau Tebyg

Markov decision processes in artificial intelligence : MDPs, beyond MDPs and applications /
gan: Sigaud, Olivier, et al.
Cyhoeddwyd: (2010)

Transience in countable MDPs
gan: Kiefer, SM, et al.
Cyhoeddwyd: (2021)

Parity objectives in countable MDPs
gan: Kiefer, S, et al.
Cyhoeddwyd: (2017)

Büchi objectives in countable MDPs
gan: Kiefer, S, et al.
Cyhoeddwyd: (2019)

Social Interactions as Recursive MDPs
gan: Tejwani, Ravi, et al.
Cyhoeddwyd: (2022)

Planning with hidden parameter polynomial MDPs
gan: Costen, C, et al.
Cyhoeddwyd: (2023)

Incorporating Rich Social Interactions Into MDPs
gan: Tejwani, Ravi, et al.
Cyhoeddwyd: (2022)

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

Combining dynamic abstractions in large MDPs
gan: Steinkraus, Kurt, et al.
Cyhoeddwyd: (2005)

Strategy complexity of parity objectives in countable MDPs
gan: Kiefer, S, et al.
Cyhoeddwyd: (2020)

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

Planning for risk-aversion and expected value in MDPs
gan: Rigter, M, et al.
Cyhoeddwyd: (2022)

Debugging of Markov Decision Processes (MDPs) Models
gan: Hichem Debbi
Cyhoeddwyd: (2016-08-01)

SEA-PARAM: Exploring Schedulers in Parametric MDPs
gan: Sebastian Arming, et al.
Cyhoeddwyd: (2017-07-01)

Batch-iFDD for representation expansion in large MDPs
gan: Geramifard, Alborz, et al.
Cyhoeddwyd: (2015)

Mixed observability MDPs for shared autonomy with uncertain human behaviour
gan: Costen, C, et al.
Cyhoeddwyd: (2021)

Adaptive Envelope MDPs for Relational Equivalence-based Planning
gan: Gardiol, Natalia H., et al.
Cyhoeddwyd: (2008)

Decomposition Methods for Solving Finite-Horizon Large MDPs
gan: Bouchra el Akraoui, et al.
Cyhoeddwyd: (2022-01-01)

Improving Probabilistic Bisimulation for MDPs Using Machine Learning
gan: Mohammadsadegh Mohagheghi, et al.
Cyhoeddwyd: (2024-06-01)

Solving Finite-Horizon Discounted Non-Stationary MDPS
gan: Bouchra El Akraoui, et al.
Cyhoeddwyd: (2023-06-01)

Probabilistic Bisimulations for PCTL Model Checking of Interval MDPs
gan: Vahid Hashemi, et al.
Cyhoeddwyd: (2014-03-01)

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

Invariant Causal Prediction for Nonlinear Models
gan: Heinze-Deml Christina, et al.
Cyhoeddwyd: (2018-09-01)

Effects of Mitochondrial-Derived Peptides (MDPs) on Mitochondrial and Cellular Health in AMD
gan: Sonali Nashine, et al.
Cyhoeddwyd: (2020-04-01)

Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
gan: Golowich, Noah, et al.
Cyhoeddwyd: (2024)

Solving uncertain MDPs with objectives that are separable over instantiations of model uncertainty
gan: Adulyasak, Yossiri, et al.
Cyhoeddwyd: (2018)

Planning large systems with MDPs: case study of inland waterways supervision
gan: Guillaume DESQUESNES, et al.
Cyhoeddwyd: (2016-12-01)

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
gan: Mao, Weichao, et al.
Cyhoeddwyd: (2023)

Provable guarantees on the robustness of decision rules to causal interventions
gan: Wang, B, et al.
Cyhoeddwyd: (2021)

Sampling Based Approaches for Minimizing Regret in Uncertain Markov Decision Processes (MDPs)
gan: Ahmed, Asrar, et al.
Cyhoeddwyd: (2021)

Finite Sample Analysis of Minmax Variant of Offline Reinforcement Learning for General MDPs
gan: Jayanth Reddy Regatti, et al.
Cyhoeddwyd: (2022-01-01)

A MDPs-Based Dynamic Path Planning in Unknown Environments for Hopping Locomotion
gan: Kosuke Sakamoto, et al.
Cyhoeddwyd: (2023-01-01)

Time-bounded mission planning in time-varying domains with semi-MDPS and Gaussian processes
gan: Duckworth, P, et al.
Cyhoeddwyd: (2021)

Strategy Complexity of Point Payoff, Mean Payoff and Total Payoff Objectives in Countable MDPs
gan: Richard Mayr, et al.
Cyhoeddwyd: (2023-03-01)

Context/Resource-Aware Mission Planning Based on BNs and Concurrent MDPs for Autonomous UAVs
gan: Chabha Hireche, et al.
Cyhoeddwyd: (2018-12-01)

Measuring Causal Invariance Formally
gan: Pierrick Bourrat
Cyhoeddwyd: (2021-05-01)

Evaluation of the Emission of Formaldehyde from Wood-Based Panels (MDFs and MDPs) in Brazil After Use
gan: José Carlos Cardozo, et al.
Cyhoeddwyd: (2023-03-01)

Characterization of MdpS: an in-depth analysis of a MUC5B-degrading protease from Streptococcus oralis
gan: Fredrik Leo, et al.
Cyhoeddwyd: (2024-01-01)

Invariance-based causal prediction to identify the direct causes of suicidal behavior
gan: Austin V. Goddard, et al.
Cyhoeddwyd: (2022-11-01)

Tangle blocks in the theory of link invariants
gan: A. Mironov, et al.
Cyhoeddwyd: (2018-09-01)