Thermodynamics of Reinforcement Learning Curricula.

Rahul V. Kulkarni

Jacob Adamczyk Juan Sebastian Rojas Rahul V. Kulkarni Thermodynamics of Reinforcement Learning Curricula. 2026 March abs/2603.12324 CoRR https://doi.org/10.48550/arXiv.2603.12324 db/journals/corr/corr2603.html#abs-2603-12324 streams/journals/corr

Jacob Adamczyk Adam Kamoski Rahul V. Kulkarni Maximum Entropy Exploration Without the Rollouts. 2026 March abs/2603.12325 CoRR https://doi.org/10.48550/arXiv.2603.12325 db/journals/corr/corr2603.html#abs-2603-12325 streams/journals/corr

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni Bootstrapped Reward Shaping. 15302-15310 2025 AAAI https://doi.org/10.1609/aaai.v39i15.33679 conf/aaai/2025 db/conf/aaai/aaai2025.html#AdamczykMTK25

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni Bootstrapped Reward Shaping. 2025 January abs/2501.00989 CoRR https://doi.org/10.48550/arXiv.2501.00989 db/journals/corr/corr2501.html#abs-2501-00989 streams/journals/corr

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni Average-Reward Reinforcement Learning with Entropy Regularization. 2025 January abs/2501.09080 CoRR https://doi.org/10.48550/arXiv.2501.09080 db/journals/corr/corr2501.html#abs-2501-09080 streams/journals/corr

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni EVAL: EigenVector-based Average-reward Learning. 2025 January abs/2501.09770 CoRR https://doi.org/10.48550/arXiv.2501.09770 db/journals/corr/corr2501.html#abs-2501-09770 streams/journals/corr

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni Boosting Soft Q-Learning by Bounding. 2373-2399 2024 RLJ 5 db/journals/rlj/rlj5.html#AdamczykMTK24 https://rlj.cs.umass.edu/2024/papers/Paper345.html

Jacob Adamczyk Volodymyr Makarenko Stas Tiomkin Rahul V. Kulkarni Boosting Soft Q-Learning by Bounding. 2024 abs/2406.18033 CoRR https://doi.org/10.48550/arXiv.2406.18033 db/journals/corr/corr2406.html#abs-2406-18033 streams/journals/corr

Jacob Adamczyk Argenis Arriojas Stas Tiomkin Rahul V. Kulkarni Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning. 6658-6665 2023 AAAI https://doi.org/10.1609/aaai.v37i6.25817 conf/aaai/2023 db/conf/aaai/aaai2023.html#AdamczykATK23 Jacob Adamczyk Volodymyr Makarenko Argenis Arriojas Stas Tiomkin Rahul V. Kulkarni Bounding the optimal value function in compositional reinforcement learning. 22-32 2023 UAI https://proceedings.mlr.press/v216/adamczyk23a.html conf/uai/2023 db/conf/uai/uai2023.html#AdamczykMATK23 Argenis Arriojas Jacob Adamczyk Stas Tiomkin Rahul V. Kulkarni Bayesian inference approach for entropy regularized reinforcement learning with stochastic dynamics. 99-109 2023 UAI https://proceedings.mlr.press/v216/arriojas23a.html conf/uai/2023 db/conf/uai/uai2023.html#ArriojasATK23

Jacob Adamczyk Stas Tiomkin Rahul V. Kulkarni Compositionality and Bounds for Optimal Value Functions in Reinforcement Learning. 2023 abs/2302.09676 CoRR https://doi.org/10.48550/arXiv.2302.09676 db/journals/corr/corr2302.html#abs-2302-09676

Jacob Adamczyk Volodymyr Makarenko Argenis Arriojas Stas Tiomkin Rahul V. Kulkarni Bounding the Optimal Value Function in Compositional Reinforcement Learning. 2023 abs/2303.02557 CoRR https://doi.org/10.48550/arXiv.2303.02557 db/journals/corr/corr2303.html#abs-2303-02557

Madeline Smith Mohammad Soltani Rahul V. Kulkarni Abhyudai Singh Modulation of stochastic gene expression by nuclear export processes. 655-660 2021 CDC https://doi.org/10.1109/CDC45484.2021.9683294 conf/cdc/2021 db/conf/cdc/cdc2021.html#SmithSKS21

Argenis Arriojas Stas Tiomkin Rahul V. Kulkarni Closed-Form Analytical Results for Maximum Entropy Reinforcement Learning. 2021 abs/2106.03931 CoRR https://arxiv.org/abs/2106.03931 db/journals/corr/corr2106.html#abs-2106-03931

Sho Inaba Carl Tony Fakhry Rahul V. Kulkarni Kourosh Zarringhalam A Free Energy Based Approach for Distance Metric Learning. 5-13 2019 KDD https://doi.org/10.1145/3292500.3330975 conf/kdd/2019 db/conf/kdd/kdd2019.html#InabaFKZ19

Niraj Kumar 0006 Abhyudai Singh Rahul V. Kulkarni Transcriptional Bursting in Gene Expression: Analytical Results for General Stochastic Models. 2015 11 PLoS Comput. Biol. 10 https://doi.org/10.1371/journal.pcbi.1004292 https://www.wikidata.org/entity/Q35810558 db/journals/ploscb/ploscb11.html#KumarSK15

Mohammad Soltani Cesar Augusto Vargas Garcia Niraj Kumar 0006 Rahul V. Kulkarni Abhyudai Singh Approximate statistical dynamics of a genetic feedback circuit. 4424-4429 2015 ACC https://doi.org/10.1109/ACC.2015.7172025 conf/amcc/2015 db/conf/amcc/acc2015.html#SoltaniVKKS15 Xiaohua Xu Niraj Kumar 0006 Arjun Krishnan Rahul V. Kulkarni Stochastic modeling of dwell-time distributions during transcriptional pausing and initiation. 4068-4073 2013 CDC https://doi.org/10.1109/CDC.2013.6760512 conf/cdc/2013 db/conf/cdc/cdc2013.html#XuKKK13

Tao Jia Rahul V. Kulkarni On the structural properties of small-world networks with finite range of shortcut links http://arxiv.org/abs/1103.0048 2011 CoRR abs/1103.0048 db/journals/corr/corr1103.html#abs-1103-0048

Jacob Adamczyk Argenis Arriojas Carl Tony Fakhry Sho Inaba Tao Jia Adam Kamoski Arjun Krishnan Niraj Kumar 0006 Volodymyr Makarenko Juan Sebastian Rojas Abhyudai Singh Madeline Smith Mohammad Soltani Stas Tiomkin César Vargas-GarcíaCesar Augusto Vargas Garcia Xiaohua Xu Kourosh Zarringhalam