CA
Christopher Amato
cs.AIcs.LGcs.ROcs.MAcs.CRstat.MLcs.CVcs.SYeess.SYcs.DC
On Valency
published · living versionsW_h48uv49n·v1 · currentpublished
Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration
with Tianle Chen, Shuo Liu
1 version
Preprints & journals
67 papers in the corpus · 2012–2026Improving LLM Collaboration via Multi-Agent Preference Learning2609.32827v1 · Shuo Liu, Xinzichen Li, Tianle Chen et al.2026 · 0 citationsarXiv
Targeting World Models to Compromise Robot Learning Pipelines2606.09499v2 · Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud et al.2026 · 0 citationsarXiv
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning2605.09212v1 · Chulabhaya Wijesundara, Andrea Baisero, Zhongheng Li et al.2026 · 0 citationsarXiv
Cross-Modal Navigation with Multi-Agent Reinforcement Learning2605.06595v1 · Shuo Liu, Xinzichen Li, Christopher Amato2026 · 0 citationsarXiv
Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning2602.05089v3 · Ethan Rathbun, Wo Wei Lin, Alina Oprea et al.2026 · 0 citationsarXiv
Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic2601.21972v5 · Shuo Liu, Tianle Chen, Ryan Amiri et al.2026 · 0 citationsarXiv
LLM Collaboration With Multi-Agent Reinforcement Learning2508.04652v7 · Shuo Liu, Tianle Chen, Zeyu Liang et al.2025 · 9 citationsarXiv
Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning2505.10484v1 · Andrea Baisero, Rupali Bhati, Shuo Liu et al.2025 · 0 citationsarXiv
Safe Multiagent Coordination via Entropic Exploration2412.20361v2 · Ayhan Alp Aydeniz, Enrico Marchesini, Robert Loftin et al.2024 · 0 citationsarXiv
Adversarial Inception Backdoor Attacks against Reinforcement Learning2410.13995v3 · Ethan Rathbun, Alina Oprea, Christopher Amato2024 · 0 citationsarXiv
An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning2409.03052v1 · Christopher Amato2024 · 19 citationsarXiv
On Stateful Value Factorization in Multi-Agent Reinforcement Learning2408.15381v2 · Enrico Marchesini, Andrea Baisero, Rupali Bhati et al.2024 · 5 citationsarXiv
Equivariant Reinforcement Learning under Partial Observability2408.14336v1 · Hai Nguyen, Andrea Baisero, David Klee et al.2024 · 4 citationsarXiv
On Centralized Critics in Multi-Agent Reinforcement Learning2408.14597v1 · Xueguang Lyu, Andrea Baisero, Yuchen Xiao et al.2024 · 24 citationsJournal of Artificial Intelligence Research 77 (2023): 295-354
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents2405.20539v2 · Ethan Rathbun, Christopher Amato, Alina Oprea2024 · 5 citationsarXiv
An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning2405.06161v7 · Christopher Amato2024 · 1 citationarXiv
Vision and Language Navigation in the Real World via Online Visual Language Mapping2310.10822v1 · Chengguang Xu, Hieu T. Nguyen, Christopher Amato et al.2023 · 0 citationsarXiv
Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control2310.02435v1 · Rohit Bokade, Xiaoning Jin, Christopher Amato2023 · 40 citationsarXiv
On-Robot Bayesian Reinforcement Learning for POMDPs2307.11954v1 · Hai Nguyen, Sammie Katt, Yuchen Xiao et al.2023 · 1 citationarXiv
Safe Deep Reinforcement Learning by Verifying Task-Level Properties2302.10030v1 · Enrico Marchesini, Luca Marzari, Alessandro Farinelli et al.2023 · 6 citationsarXiv
Improving Deep Policy Gradients with Value Function Search2302.10145v1 · Enrico Marchesini, Christopher Amato2023 · 2 citationsarXiv
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning2301.11321v3 · Brett Daley, Martha White, Christopher Amato et al.2023 · 0 citationsarXiv
Leveraging Fully Observable Policies for Learning under Partial Observability2211.01991v2 · Hai Nguyen, Andrea Baisero, Dian Wang et al.2022 · 5 citationsarXiv
Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning2209.10113v2 · Yuchen Xiao, Weihao Tan, Christopher Amato2022 · 19 citationsarXiv
Deep Transformer Q-Networks for Partially Observable Reinforcement Learning2206.01078v2 · Kevin Esslinger, Robert Platt, Christopher Amato2022 · 18 citationsarXiv
Hierarchical Reinforcement Learning under Mixed Observability2204.00898v3 · Hai Nguyen, Zhihan Yang, Andrea Baisero et al.2022 · 3 citationsarXiv
BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs2202.08884v1 · Sammie Katt, Hai Nguyen, Frans A. Oliehoek et al.2022 · 2 citationsarXiv
A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning2201.01221v2 · Xueguang Lyu, Andrea Baisero, Yuchen Xiao et al.2022 · 10 citationsThirty-Sixth AAAI Conference on Artificial Intelligence 2022 (AAAI-22)
Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting for Past Decisions2112.12281v1 · Brett Daley, Christopher Amato2021 · 1 citationarXiv
Virtual Replay Cache2112.03421v1 · Brett Daley, Christopher Amato2021 · 0 citationsarXiv
Human-Level Control without Server-Grade Hardware2111.01264v1 · Brett Daley, Christopher Amato2021 · 0 citationsarXiv
Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning2110.08642v3 · Yuchen Xiao, Xueguang Lyu, Christopher Amato2021 · 11 citationsIEEE The 3rd International Symposium on Multi-Robot and Multi-Agent Systems (MRS), 2021
Investigating Alternatives to the Root Mean Square for Adaptive Gradient Methods2106.05449v1 · Brett Daley, Christopher Amato2021 · 0 citationsarXiv
Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps2106.03665v1 · Chengguang Xu, Christopher Amato, Lawson L.S. Wong2021 · 3 citationsarXiv
Reconciling Rewards with Predictive State Representations2106.03926v1 · Andrea Baisero, Christopher Amato2021 · 1 citationProceedings of the Thirtieth International Joint Conference on Artificial Intelligence (2021) Pages 2170-2176
Unbiased Asymmetric Reinforcement Learning under Partial Observability2105.11674v2 · Andrea Baisero, Christopher Amato2021 · 9 citationsProceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, pp. 44-52. 2022
End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning2104.12842v1 · Mohammadreza Sharif, Deniz Erdogmus, Christopher Amato et al.2021 · 4 citationsarXiv
Decentralized Reinforcement Learning for Multi-Target Search and Detection by a Team of Drones2103.09520v1 · Roi Yehoshua, Juan Heredia-Juesas, Yushu Wu et al.2021 · 2 citationsarXiv
Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning2102.11319v1 · Brett Daley, Cameron Hickert, Christopher Amato2021 · 5 citationsarXiv
Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning2102.04402v2 · Xueguang Lyu, Yuchen Xiao, Brett Daley et al.2021 · 74 citationsProceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2021
Safe Multi-Agent Reinforcement Learning via Shielding2101.11196v2 · Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato et al.2021 · 56 citationsarXiv
Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability2010.09170v5 · Hai Nguyen, Brett Daley, Xinchao Song et al.2020 · 7 citationsarXiv
Expectigrad: Fast Stochastic Optimization with Robust Convergence Properties2010.01356v2 · Brett Daley, Christopher Amato2020 · 3 citationsarXiv
Macro-Action-Based Deep Multi-Agent Reinforcement Learning2004.08646v2 · Yuchen Xiao, Joshua Hoffman, Christopher Amato2020 · 16 citations3rd Conference on Robot Learning (CoRL 2019)
Active Goal Recognition1909.11173v1 · Christopher Amato, Andrea Baisero2019 · 1 citationarXiv
Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net1909.08776v2 · Yuchen Xiao, Joshua Hoffman, Tian Xia et al.2019 · 31 citationsarXiv
Modeling and Planning with Macro-Actions in Decentralized POMDPs.31656393 · Amato, Christopher, Konidaris, George, Kaelbling, Leslie P et al.2020 · 64 citationsThe journal of artificial intelligence research. 2019;64:817-859
Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning1812.06319v6 · Xueguang Lyu, Christopher Amato2018 · 20 citationsProceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pp. 798-806. 2020
Bayesian Reinforcement Learning in Factored POMDPs1811.05612v1 · Sammie Katt, Frans Oliehoek, Christopher Amato2018 · 15 citationsarXiv
Reconciling -Returns with Experience Replay1810.09967v3 · Brett Daley, Christopher Amato2018 · 21 citationsarXiv
Career total: 199 works. 67 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.