Multi-Agent Reinforcement Learning 🤖🤖 | Partially Observable RL | Robotics | Led by Chris Amato @cjdamato @KhouryCollege @Northeastern
Boston, Massachusetts
Joined May 2022
- Tweets20
- Following22
- Followers80
- Likes25
Lab for Learning and Planning in Robotics retweeted
This Friday (02 Feb) we will have @LyuXueguang presenting his work on Centralized Critics. See y'all on Friday 9AM (PT)/12noon (ET).
Lab for Learning and Planning in Robotics retweeted
Happy to share our #CoRL23 paper about leveraging symmetry for POMDPs. We formulate group-invariant POMDPs that are symmetric in the history space. As expected, equivariant recurrent policies shine in solving them. For more, please see sites.google.com/view/equi-r….
Lab for Learning and Planning in Robotics retweeted
New #IROS2023 paper alert: A Bayesian-Adaptive RL with mixed observability assumption, training directly on hardware, greatly more sample-efficient >> RL methods. Joint w/ SammieKatt @YuchenXiao5 @cjdamato @LLPR_NEU.
Paper:Â arxiv.org/abs/2307.11954
Video: youtube.com/watch?v=H9xp60ng…
Lab for Learning and Planning in Robotics retweeted
Looking for novel ways to improve value approximation and analyzing the effects on Deep Policy Gradient algorithms?
Check out our "Improving Deep Policy Gradients with Value Function Search" paper at @iclr_conf with @cjdamato ! iclr.cc/virtual/2023/poster/…
Lab for Learning and Planning in Robotics retweeted
I am thrilled to announce that I will be joining @Northeastern University for the PhD in CS program with @cjdamato! Super excited to join this lab!
Lab for Learning and Planning in Robotics retweeted
Congrats to my PhD student Sammie Katt for passing his defense titled "Bayesian Partial Observable Reinforcement Learning." Very cool work, Sammie! (with @faoliehoek, @RobotPlatt, and Lawson Wong).
Lab for Learning and Planning in Robotics retweeted
We(@cjdamato) recently published MacroMARL(github.com/yuchen-x/MacroMAR…), including both value-based and policy-gradient-based algorithms for multi-agent asynchronous learning and execution, as well as three macro-action-based multi-agent domains. To find more, please check it out!
Lab for Learning and Planning in Robotics retweeted
Interested in partial observability? Come to my online poster session at @CoRL2022 (online session 2, Sunday, Dec 18, 7:30-8.00 AM, Auckland time, i.e., Saturday, Dec 17, 1:30 - 2:00 PM, EST time) w/ @RobotPlatt @cjdamato @DianWang1007 @AndreaBaisero @LLPR_NEU @HelpingHandsLab.
Glad to share our #CoRL22 paper arxiv.org/abs/2211.01991 about using MDP solutions to efficiently learn POMDPs during offline training. We proposed a SAC-like agent that balances between acting like an MDP expert and for environment rewards.
LLPR member @cjdamato explains our asynchronous actor critic method for Multi-agent RL #NeurIPS2022
Lab for Learning and Planning in Robotics retweeted
Tmr(Thurs), 4-6pm, Hall J 613 #NeurIPS2022, my advisor Chris @cjdamato is going to present how we enable agents to asynchronously learn and execute. Please stop by to check the details and know more about the lab @LLPR_NEU. Also, feel free to contact me for any questions!
I am very excited to share that our paper "Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning" (arxiv.org/abs/2209.10113) has been accepted to #NeurIPS2022. A step towards asynchronous and hierarchical behaviors in real-world multi-agent/robot systems.
LLPR member Daniel Melcer shows decentralized shielding can be an effective solution for multi-agent RL and doesn’t require communication between agents #NeurIPS2022
Link to paper: openreview.net/pdf?id=JO9o3D…
Daniel’s paper was selected as an Oral at #NeurIPS2022 !
Lab for Learning and Planning in Robotics retweeted
We have 2 papers in the main conference #NeurIPS2022.
Poster: Wed 5-7
Shield Decentralization for Safe Multi-Agent Reinforcement Learning
neurips.cc/virtual/2022/post…
Poster: Thurs 5-7
Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning:
neurips.cc/virtual/2022/post…
On our way to New Orleans for @NeurIPSConf! Be sure to catch up with LLPR members @cjdamato, @LyuXueguang, Daniel Melcer, and @kevslinger this week
Lab for Learning and Planning in Robotics retweeted
Are you curious about pursuing a PhD in CS with a focus in software, programming languages, or systems and formal methods? Join our fourth PhD info session hosted by professor Steven Holtzen, @zengola, on November 21! Register now at the link below.
bit.ly/3VcXLcQ
Lab for Learning and Planning in Robotics retweeted
I'm looking for PhD students for Fall 2023! Anyone interested in partially observable or multi-agent reinforcement learning (MARL) is welcome to apply but I'm particularly looking for people with a background and interest in MARL for multi-robot systems.
khoury.northeastern.edu/appl…
Lab for Learning and Planning in Robotics retweeted
Glad to share our #CoRL22 paper arxiv.org/abs/2211.01991 about using MDP solutions to efficiently learn POMDPs during offline training. We proposed a SAC-like agent that balances between acting like an MDP expert and for environment rewards.
Lab for Learning and Planning in Robotics retweeted
A bit late, but check out @YuchenXiao5's talk at the #IROS2022 Decision-Making in Multi-Agent Systems workshop!
dcslgatech.github.io/iros22-…