pith. sign in

arxiv: 2606.25978 · v1 · pith:AR42MIOInew · submitted 2026-06-24 · 💻 cs.MA · cs.AI· cs.LG

Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

Thiago Thomas , Gabriel de Oliveira Ramos , Felipe Meneguzzi This is my paper

Pith reviewed 2026-06-25 18:58 UTC · model grok-4.3

classification 💻 cs.MA cs.AIcs.LG
keywords multi-agent goal recognitionbranch-and-boundreinforcement learningteam recognitionhypothesis rankingBlocksworldmulti-agent systems
0
0 comments X

The pith

MAGR-BB matches exhaustive search top hypothesis in multi-agent goal recognition while evaluating orders of magnitude fewer options.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces MAGR-BB for jointly inferring agent teams and their goals from observed trajectories alone. It places a single team- and goal-conditioned reinforcement learning policy inside a factorized branch-and-bound procedure to score and prune hypotheses. On a controlled multi-agent Blocksworld benchmark the method returns identical top-ranked hypotheses to full enumeration at every step along each trajectory. The approach therefore avoids materializing the full combinatorial space of team partitions and goals.

Core claim

MAGR-BB addresses multi-agent goal recognition by using a shared team- and goal-conditioned policy as the scoring model inside a factorized branch-and-bound search, returning the same top-ranked hypothesis as exhaustive search throughout the trajectory on a controlled multi-agent Blocksworld benchmark while cutting hypothesis materialization by orders of magnitude and reducing cumulative recognition runtime substantially.

What carries the argument

factorized branch-and-bound search guided by a shared team- and goal-conditioned reinforcement learning policy used as the scoring model

Load-bearing premise

A single shared team- and goal-conditioned RL policy supplies accurate enough and consistent enough scores to guarantee the identical top-ranked hypothesis as exhaustive enumeration across every timestep of the chosen benchmark trajectories.

What would settle it

A multi-agent Blocksworld trajectory where the top-ranked team-goal hypothesis returned by MAGR-BB differs from the one returned by exhaustive enumeration at any point along the sequence.

Figures

Figures reproduced from arXiv: 2606.25978 by Felipe Meneguzzi, Gabriel de Oliveira Ramos, Thiago Thomas.

Figure 1
Figure 1. Figure 1: Runtime and workload across the six variants. Top row: cumulative runtime versus action [PITH_FULL_IMAGE:figures/full_fig_p009_1.png] view at source ↗
read the original abstract

Multi-agent goal recognition asks an observer to jointly infer which agents act together and what each team is trying to achieve, so the hypothesis space grows combinatorially with the number of team partitions and goals per team. Real applications such as drone surveillance and collaborative robotics expose only the agents' trajectory, which forces the observer to rank team-goal hypotheses from behavior alone. Multi-Agent Goal Recognition with Branch-and-Bound (MAGR-BB) addresses this setting with a shared team- and goal-conditioned policy used as the scoring model inside a factorized branch-and-bound search. On a controlled multi-agent Blocksworld benchmark, MAGR-BB returns the same top-ranked hypothesis as exhaustive search throughout the trajectory while cutting hypothesis materialization by orders of magnitude and reducing cumulative recognition runtime substantially.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript proposes MAGR-BB, a method for multi-agent goal recognition that employs a shared team- and goal-conditioned reinforcement learning policy as the scoring model inside a factorized branch-and-bound search. The central empirical claim, evaluated on a controlled multi-agent Blocksworld benchmark, is that MAGR-BB recovers the identical top-ranked hypothesis as exhaustive search at every step along the trajectory while materializing orders of magnitude fewer hypotheses and substantially reducing cumulative recognition runtime.

Significance. If the reported equivalence to exhaustive enumeration holds on the evaluated instances, the work demonstrates a practical way to address the combinatorial explosion in joint team-partition and goal hypotheses for goal recognition from trajectories alone. The combination of RL-based scoring with factorized search is technically interesting and could support applications such as surveillance or collaborative robotics, provided the approach generalizes beyond the specific benchmark.

minor comments (2)
  1. The abstract asserts equivalence and efficiency gains but does not report the number of benchmark instances evaluated, any measures of statistical significance, error rates, or ablation results on the RL policy; these details are needed to substantiate the central empirical claim even if present in later sections.
  2. Clarify how the factorized branch-and-bound avoids materializing full hypotheses during pruning and whether the RL policy is trained on the same distribution of team-goal combinations used at test time.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of MAGR-BB and the recommendation for minor revision. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper trains a shared team- and goal-conditioned RL policy separately and deploys it as a scoring function inside a factorized branch-and-bound search. The central empirical claim is that this combination recovers the identical top-ranked hypothesis as exhaustive enumeration on the reported Blocksworld instances while materializing far fewer hypotheses. No equation or step reduces the reported outcome to a definitional identity, a fitted parameter renamed as a prediction, or a self-citation chain that forces the result by construction. The equivalence to exhaustive search is presented as an experimental observation on controlled benchmarks rather than a logical necessity derived from the method's own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, preventing extraction of specific free parameters, axioms, or invented entities; the approach implicitly relies on standard RL training assumptions and benchmark construction details not stated here.

pith-pipeline@v0.9.1-grok · 5670 in / 1057 out tokens · 21595 ms · 2026-06-25T18:58:17.445166+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

60 extracted references · 27 canonical work pages · 1 internal anchor

  1. [1]

    and Allen, James F

    Kautz, Henry A. and Allen, James F. , booktitle =. Generalized plan recognition , year =

  2. [2]

    , booktitle =

    Geib, Christopher W. , booktitle =. Problems with Intent Recognition for Elder Care , year =

  3. [3]

    Automated Planning: Theory & Practice , year =

    Nau, Dana and Ghallab, Malik and Traverso, Paolo , publisher =. Automated Planning: Theory & Practice , year =

  4. [6]

    Proceedings of the 21st International Joint Conference on Artificial Intelligence , title =

    Ram\'. Proceedings of the 21st International Joint Conference on Artificial Intelligence , title =. 2009 , address =

    2009

  5. [7]

    and Dang, Viet Dung and Jennings, Nicholas R

    Rahwan, Talal and Ramchurn, Sarvapali D. and Dang, Viet Dung and Jennings, Nicholas R. , booktitle =. Near-optimal anytime coalition structure generation , year =

  6. [11]

    Action-Model Based Multi-agent Plan Recognition , year =

    Zhuo, Hankz and Yang, Qiang and Kambhampati, Subbarao , booktitle =. Action-Model Based Multi-agent Plan Recognition , year =

  7. [12]

    Sturtevant, N. R. , journal =. Benchmarks for Grid-Based Pathfinding , year =. doi:10.1109/tciaig.2012.2197681 , publisher =

    work page doi:10.1109/tciaig.2012.2197681 2012

  8. [13]

    A Concise Introduction to Models and Methods for Automated Planning: Synthesis Lectures on Artificial Intelligence and Machine Learning , year =

    Geffner, Hector and Bonet, Blai , publisher =. A Concise Introduction to Models and Methods for Automated Planning: Synthesis Lectures on Artificial Intelligence and Machine Learning , year =

  9. [14]

    , publisher =

    Sukthankar, Gita and Geib, Christopher and Bui, Hung Hai and Pynadath, David and Goldman, Robert P. , publisher =. Plan, Activity, and Intent Recognition: Theory and Practice , year =

  10. [17]

    Proceedings of the 26th Annual International Conference on Machine Learning , title =

    Bengio, Yoshua and Louradour, J. Proceedings of the 26th Annual International Conference on Machine Learning , title =. 2009 , pages =

    2009

  11. [18]

    Asynchronous Methods for Deep Reinforcement Learning , booktitle =

    Mnih, Volodymyr and Badia, Adri. Asynchronous Methods for Deep Reinforcement Learning , booktitle =. 2016 , editor =

    2016

  12. [19]

    Proximal Policy Optimization Algorithms

    Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg , title =. 2017 , copyright =. doi:10.48550/ARXIV.1707.06347 , keywords =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1707.06347 2017

  13. [20]

    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , year =

    Lowe, Ryan and Wu, Yi and Tamar, Aviv and Harb, Jean and Abbeel, Pieter and Mordatch, Igor , booktitle =. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , year =

  14. [21]

    and Barto, Andrew G

    Sutton, Richard S. and Barto, Andrew G. , publisher =. Reinforcement Learning: An Introduction , year =

  15. [23]

    New Goal Recognition Algorithms Using Attack Graphs , year =

    Mirsky, Reuth and Shalom, Ya'ar and Majadly, Ahmad and Gal, Kobi and Puzis, Rami and Felner, Ariel , pages =. New Goal Recognition Algorithms Using Attack Graphs , year =. Cyber Security Cryptography and Machine Learning , doi =

  16. [26]

    and Swaminathan, Chittaranjan S

    Rudenko, Andrey and Kucner, Tomasz P. and Swaminathan, Chittaranjan S. and Chadalavada, Ravi T. and Arras, Kai O. and Lilienthal, Achim J. , journal =. 2020 , number =. doi:10.1109/LRA.2020.2965416 , groups =

    work page doi:10.1109/lra.2020.2965416 2020

  17. [29]

    and Brewitt, Cillian and Wilhelm, John and Gyevnar, Balint and Eiras, Francisco and Dobre, Mihai and Ramamoorthy, Subramanian , booktitle =

    Albrecht, Stefano V. and Brewitt, Cillian and Wilhelm, John and Gyevnar, Balint and Eiras, Francisco and Dobre, Mihai and Ramamoorthy, Subramanian , booktitle =. Interpretable Goal-based Prediction and Planning for Autonomous Driving , year =

  18. [30]

    Metadrive: Composing diverse driving scenarios for generalizable reinforcement learning , year =

    Li, Quanyi and Peng, Zhenghao and Feng, Lan and Zhang, Qihang and Xue, Zhenghai and Zhou, Bolei , journal =. Metadrive: Composing diverse driving scenarios for generalizable reinforcement learning , year =

  19. [32]

    Universal Value Function Approximators , year =

    Schaul, Tom and Horgan, Dan and Gregor, Karol and Silver, David , booktitle =. Universal Value Function Approximators , year =

  20. [33]

    Goal-Conditioned Reinforcement Learning: Problems and Solutions , year =

    Liu, Minghuan and Zhu, Menghui and Zhang, Weinan , booktitle =. Goal-Conditioned Reinforcement Learning: Problems and Solutions , year =

  21. [37]

    Albrecht and Filippos Christianos and Lukas Sch\"afer , publisher =

    Stefano V. Albrecht and Filippos Christianos and Lukas Sch\"afer , publisher =. Multi-Agent Reinforcement Learning: Foundations and Modern Approaches , year =

  22. [38]

    and Kaiser, Lukasz and Polosukhin, Illia , booktitle =

    Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia , booktitle =. Attention Is All You Need , year =

  23. [40]

    2025 , archiveprefix =

    Meng Feng and Viraj Parimi and Brian Williams , title =. 2025 , archiveprefix =. 2502.17813 , groups =

    arXiv 2025

  24. [42]

    and Iocchi, L

    Farinelli, A. and Iocchi, L. and Nardi, D. , journal =. Multirobot Systems: A Classification Focused on Coordination , year =

  25. [44]

    Mohamed Abdelkader, Samet G \"u ler, Hassan Jaleel, and Jeff S. Shamma. Aerial swarms: Recent applications and challenges. Current Robotics Reports, 2 0 (3): 0 309--320, 2021. ISSN 2662-4087. doi:10.1007/s43154-021-00063-4. URL https://doi.org/10.1007/s43154-021-00063-4

    work page doi:10.1007/s43154-021-00063-4 2021

  26. [45]

    In: 2021 IEEE International Conference on Robotics and Automation (ICRA)

    Stefano V. Albrecht, Cillian Brewitt, John Wilhelm, Balint Gyevnar, Francisco Eiras, Mihai Dobre, and Subramanian Ramamoorthy. Interpretable goal-based prediction and planning for autonomous driving. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 1043--1049. IEEE, May 2021. doi:10.1109/icra48506.2021.9560849

    work page doi:10.1109/icra48506.2021.9560849 2021

  27. [46]

    Albrecht, Filippos Christianos, and Lukas Sch\"afer

    Stefano V. Albrecht, Filippos Christianos, and Lukas Sch\"afer. Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press, 2024. URL https://www.marl-book.com

    2024

  28. [47]

    Goal recognition as reinforcement learning

    Leonardo Amado, Reuth Mirsky, and Felipe Meneguzzi. Goal recognition as reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36 0 (9): 0 9644--9651, Jun. 2022. doi:10.1609/aaai.v36i9.21198. URL https://ojs.aaai.org/index.php/AAAI/article/view/21198

    work page doi:10.1609/aaai.v36i9.21198 2022

  29. [48]

    A survey on model-free goal recognition

    Leonardo Amado, Sveta Paster Shainkopf, Ramon Fraga Pereira, Reuth Mirsky, and Felipe Meneguzzi. A survey on model-free goal recognition. In Kate Larson, editor, Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24 , pages 7923--7931. International Joint Conferences on Artificial Intelligence Organization, 8 ...

    work page doi:10.24963/ijcai.2024/877 2024

  30. [49]

    Multi-agent plan recognition as planning (maprap)

    Chris Argenta and Jon Doyle. Multi-agent plan recognition as planning (maprap). In Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,, pages 141--148. INSTICC, SciTePress, 2016. ISBN 978-989-758-172-4. doi:10.5220/0005707701410148

    work page doi:10.5220/0005707701410148 2016

  31. [50]

    Probabilistic multi-agent plan recognition as planning (p-maprap): Recognizing teams, goals, and plans from action sequences

    Chris Argenta and Jon Doyle. Probabilistic multi-agent plan recognition as planning (p-maprap): Recognizing teams, goals, and plans from action sequences. In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,, pages 575--582. INSTICC, SciTePress, 2017. ISBN 978-989-758-220-2. doi:10.5220/0006197505750582

    work page doi:10.5220/0006197505750582 2017

  32. [51]

    Multi-agent plan recognition: Formalization and algorithms

    Bikramjit Banerjee, Landon Kraemer, and Jeremy Lyle. Multi-agent plan recognition: Formalization and algorithms. Proceedings of the AAAI Conference on Artificial Intelligence, 24 0 (1): 0 1059--1064, Jul. 2010. doi:10.1609/aaai.v24i1.7746. URL https://ojs.aaai.org/index.php/AAAI/article/view/7746

    work page doi:10.1609/aaai.v24i1.7746 2010

  33. [52]

    Curriculum learning

    Yoshua Bengio, J \'e r \^o me Louradour, Ronan Collobert, and Jason Weston. Curriculum learning. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 41--48. ACM, 2009. doi:10.1145/1553374.1553380

    work page doi:10.1145/1553374.1553380 2009

  34. [53]

    Goal recognition as a deep learning task: The grnet approach

    Mattia Chiari, Alfonso Emilio Gerevini, Francesco Percassi, Luca Putelli, Ivan Serina, and Matteo Olivato. Goal recognition as a deep learning task: The grnet approach. Proceedings of the International Conference on Automated Planning and Scheduling, 33 0 (1): 0 560--568, July 2023. ISSN 2334-0835. doi:10.1609/icaps.v33i1.27237

    work page doi:10.1609/icaps.v33i1.27237 2023

  35. [54]

    Multi-agent intention recognition and progression

    Michael Dann, Yuan Yao, Natasha Alechina, Brian Logan, Felipe Meneguzzi, and John Thangarajah. Multi-agent intention recognition and progression. In Edith Elkind, editor, Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23 , pages 91--99. International Joint Conferences on Artificial Intelligence Organizati...

    work page doi:10.24963/ijcai.2023/11 2023

  36. [55]

    Prediction of intent in robotics and multi-agent systems

    Yiannis Demiris. Prediction of intent in robotics and multi-agent systems. Cognitive Processing, 8 0 (3): 0 151--158, May 2007. ISSN 1612-4790. doi:10.1007/s10339-007-0168-9

    work page doi:10.1007/s10339-007-0168-9 2007

  37. [56]

    Real-time online goal recognition in continuous domains via deep reinforcement learning

    Zihao Fang, Dejun Chen, Yunxiu Zeng, Tao Wang, and Kai Xu. Real-time online goal recognition in continuous domains via deep reinforcement learning. Entropy, 25 0 (10): 0 1415, October 2023. ISSN 1099-4300. doi:10.3390/e25101415

    work page doi:10.3390/e25101415 2023

  38. [57]

    Farinelli, L

    A. Farinelli, L. Iocchi, and D. Nardi. Multirobot systems: A classification focused on coordination. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 34 0 (5): 0 2015--2028, 2004. doi:10.1109/TSMCB.2004.832155

    work page doi:10.1109/tsmcb.2004.832155 2015

  39. [58]

    A Concise Introduction to Models and Methods for Automated Planning: Synthesis Lectures on Artificial Intelligence and Machine Learning

    Hector Geffner and Blai Bonet. A Concise Introduction to Models and Methods for Automated Planning: Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 1st edition, 2013. ISBN 1608459691

    2013

  40. [59]

    Geib and Robert P

    Christopher W. Geib and Robert P. Goldman. A probabilistic plan recognition algorithm based on plan tree grammars. Artificial Intelligence, 173 0 (11): 0 1101--1132, 2009. ISSN 0004-3702. doi:https://doi.org/10.1016/j.artint.2009.01.003. URL https://www.sciencedirect.com/science/article/pii/S0004370209000459

    work page doi:10.1016/j.artint.2009.01.003 2009

  41. [60]

    Kautz and James F

    Henry A. Kautz and James F. Allen. Generalized plan recognition. In Proceedings of the Fifth AAAI National Conference on Artificial Intelligence, AAAI'86, pages 32--37. AAAI Press, 1986

    1986

  42. [61]

    E. L. Lawler and D. E. Wood. Branch-and-bound methods: A survey. Operations Research, 14 0 (4): 0 699--719, 1966. ISSN 0030364X, 15265463. doi:10.1287/opre.14.4.699. URL http://www.jstor.org/stable/168733

    work page doi:10.1287/opre.14.4.699 1966

  43. [62]

    Goal-conditioned reinforcement learning: Problems and solutions

    Minghuan Liu, Menghui Zhu, and Weinan Zhang. Goal-conditioned reinforcement learning: Problems and solutions. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-2022, pages 5502--5511. International Joint Conferences on Artificial Intelligence Organization, July 2022. doi:10.24963/ijcai.2022/770

    work page doi:10.24963/ijcai.2022/770 2022

  44. [63]

    Multi-agent actor-critic for mixed cooperative-competitive environments

    Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, and Igor Mordatch. Multi-agent actor-critic for mixed cooperative-competitive environments. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30, pages 6379--6390. Curran Associates, Inc., ...

    2017

  45. [64]

    A survey on goal recognition as planning

    Felipe Meneguzzi and Ramon Fraga Pereira. A survey on goal recognition as planning. In Zhi-Hua Zhou, editor, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 , pages 4524--4532. International Joint Conferences on Artificial Intelligence Organization, 8 2021. doi:10.24963/ijcai.2021/616. URL https://doi.org/1...

    work page doi:10.24963/ijcai.2021/616 2021

  46. [65]

    New Goal Recognition Algorithms Using Attack Graphs, pages 260--278

    Reuth Mirsky, Ya'ar Shalom, Ahmad Majadly, Kobi Gal, Rami Puzis, and Ariel Felner. New Goal Recognition Algorithms Using Attack Graphs, pages 260--278. Springer International Publishing, 2019. ISBN 9783030209513. doi:10.1007/978-3-030-20951-3_23

    work page doi:10.1007/978-3-030-20951-3_23 2019

  47. [66]

    Reuth Mirsky, Sarah Keren, and Christopher W. Geib. Introduction to Symbolic Plan and Goal Recognition. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2021. doi:10.2200/S01062ED1V01Y202012AIM047. URL https://doi.org/10.2200/S01062ED1V01Y202012AIM047

    work page doi:10.2200/s01062ed1v01y202012aim047 2021

  48. [67]

    Automated Planning: Theory & Practice

    Dana Nau, Malik Ghallab, and Paolo Traverso. Automated Planning: Theory & Practice. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2004. ISBN 1558608567

    2004

  49. [68]

    Landmark-based approaches for goal recognition as planning

    Ramon Fraga Pereira, Nir Oren, and Felipe Meneguzzi. Landmark-based approaches for goal recognition as planning. Artificial Intelligence, 279: 0 103217, February 2020. ISSN 0004-3702. doi:10.1016/j.artint.2019.103217

    work page doi:10.1016/j.artint.2019.103217 2020

  50. [69]

    Ramchurn, Viet Dung Dang, and Nicholas R

    Talal Rahwan, Sarvapali D. Ramchurn, Viet Dung Dang, and Nicholas R. Jennings. Near-optimal anytime coalition structure generation. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, IJCAI'07, pages 2365--2371, San Francisco, CA, USA, 2007. Morgan Kaufmann Publishers Inc

    2007

  51. [70]

    Probabilistic plan recognition using off-the-shelf classical planners

    Miguel Ram \'i rez and Hector Geffner. Probabilistic plan recognition using off-the-shelf classical planners. Proceedings of the AAAI Conference on Artificial Intelligence, 24 0 (1): 0 1121--1126, Jul. 2010. doi:10.1609/aaai.v24i1.7745. URL https://ojs.aaai.org/index.php/AAAI/article/view/7745

    work page doi:10.1609/aaai.v24i1.7745 2010

  52. [71]

    Plan recognition as planning

    Miquel Ram\' rez and Hector Geffner. Plan recognition as planning. In Proceedings of the 21st International Joint Conference on Artificial Intelligence, IJCAI'09, pages 1778--1783, San Francisco, CA, USA, 2009. Morgan Kaufmann Publishers Inc

    2009

  53. [72]

    Universal value function approximators

    Tom Schaul, Dan Horgan, Karol Gregor, and David Silver. Universal value function approximators. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 1312--1320. PMLR, 2015. URL https://proceedings.mlr.press/v37/schaul15.html

    2015

  54. [73]

    Proximal policy optimization algorithms, 2017

    John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms, 2017

    2017

  55. [74]

    Combining gaze and ai planning for online human intention recognition

    Ronal Singh, Tim Miller, Joshua Newn, Eduardo Velloso, Frank Vetere, and Liz Sonenberg. Combining gaze and ai planning for online human intention recognition. Artificial Intelligence, 284: 0 103275, 2020. ISSN 0004-3702. doi:https://doi.org/10.1016/j.artint.2020.103275. URL https://www.sciencedirect.com/science/article/pii/S0004370218307628

    work page doi:10.1016/j.artint.2020.103275 2020

  56. [75]

    Blocks World revisited , journal =

    John Slaney and Sylvie Thi\' e baux. Blocks W orld revisited. Artificial Intelligence, 125 0 (1--2): 0 119--153, 2001. ISSN 0004-3702. doi:10.1016/S0004-3702(00)00079-5

    work page doi:10.1016/s0004-3702(00)00079-5 2001

  57. [76]

    Gita Sukthankar, Christopher Geib, Hung Hai Bui, David Pynadath, and Robert P. Goldman. Plan, Activity, and Intent Recognition: Theory and Practice. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1st edition, 2014. ISBN 0123985323

    2014

  58. [77]

    Gomez, Lukasz Kaiser, and Illia Polosukhin

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30, pages 5998--6008. Curran Associates, I...

    2017

  59. [78]

    Action-model based multi-agent plan recognition

    Hankz Zhuo, Qiang Yang, and Subbarao Kambhampati. Action-model based multi-agent plan recognition. In F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 25. Curran Associates, Inc., 2012. URL https://proceedings.neurips.cc/paper_files/paper/2012/file/a597e50502f5ff68e3e25b9114205d4a-...

    2012

  60. [79]

    Recognizing multi-agent plans when action models and team plans are both incomplete

    Hankz Hankui Zhuo. Recognizing multi-agent plans when action models and team plans are both incomplete. ACM Trans. Intell. Syst. Technol., 10 0 (3), may 2019. ISSN 2157-6904. doi:10.1145/3319403. URL https://doi.org/10.1145/3319403

    work page doi:10.1145/3319403 2019