Professor of Computing Science at the University of Alberta. Interested in AI, machine learning, and games of all sorts.
Edmonton, Alberta
Joined March 2017
- Tweets247
- Following90
- Followers2.5K
- Likes534
Michael Bowling retweeted
@richardssutton has received the A.M. Turing Award, the highest honour in computer science. How did he get here, and what’s next for this Amii Fellow & Canada @CIFAR_News AI Chair? Read more: hubs.la/Q039ws7h0
#AI #ReinforcementLearning #TuringAward
There needs more thinking on this! Find us in the poster session Wednesday @ 4:30pm #6500.
Is there a hyperparameter crisis in reinforcement learning? Let's talk about it at NeurIPS. #NeurIPS2024
Michael Bowling retweeted
@UAlberta is doing an AI Cohort Hire for 20+ faculty positions all across campus, with a specific focus on AI+Science, e.g., drug discovery. Successful candidates will be nominated for a CIFAR AI Chair with generous funding! Find out more: apps.ualberta.ca/careers/pos….
Michael Bowling retweeted
I was evacuated from #Jasper while camping with my husband and two young kids this week. This is my #jasperwildfire story. We arrived at Wabasso campground Sunday afternoon. It was 34 degrees, and the man at the check in booth was sweating profusely in the heat. He (1/22)
Super excited that I've gotten to see behind the scenes of what they're doing. This is an amazing team (and I've been lucky to work with many of them) doing amazing things!
The future of gaming is here! Today we officially emerged from stealth and announced $16M (USD) in funding. Thanks to our investors (@radicalvcfund, @Toyota_Ventures, @flyingfishVC and others) and our incredible team for getting us here. Let's go!
artificial.agency/news/artif…
1
11
757
While there's real concerns about generative AI and game dev, there's also so many new opportunities for radically new game experiences. Can't wait to see what's next, @ArtificialAgncy.
4
246
Michael Bowling retweeted
Are rewards always observable to the agent?
At #AAMAS 2024, I'll present Mon-MDP a novel framework where rewards are not always observable to the agent
Collaboration with Simone Parisi, Alireza Kazemipour Matthew Taylor @MichaelHBowling
arxiv.org/abs/2402.06819
Michael Bowling retweeted
Thrilled to announce the first annual Reinforcement Learning Conference @RL_Conference, which will be held at UMass Amherst August 9-12!
RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.
Michael Bowling retweeted
Excited to announce our @RL_Conference workshop, Finding the Frame 🖼️.
We encourage submissions reflecting broadly on the conceptual foundations of RL and their impact on framing problems.
See the thread below and follow our account for more info!
🚨Announcing 🫸Finding the Frame🫷: an @RL_Conference workshop for examining conceptual frameworks in RL!🚨
Do you want to question formulations or practices in RL? Define new problems, challenge assumptions, or test the limits of RL paradigms?
Join us!
sites.google.com/view/findin…
Michael Bowling retweeted
Artificial.Agency is building the behavior engine driving the future of interactive digital entertainment.
We are co-creating the next level of gaming with our studio partners and you’re invited to be part of the journey.
Join our pilot.
artificial.agency/
This is a great team doing great stuff!
We have built DeepStack, the first AI to beat humans in no-limit poker.
We are now building the next generation AI company for algorithmic trading!
We are growing our research and engineering team.
If you want to work with a world class AI team led by ex-DeepMind researchers and engineers.
If you want to build something that has never been done before - join us.
equilibretechnologies.com
Michael Bowling retweeted
after many years of work, I've very excited that our general game playing algorithm, Student of Games, is being published in Science Advances today
in it, we present a general algorithm for games of both perfect and imperfect information
(work was done while I was at DeepMind)
Michael Bowling retweeted
⚽🌐🕸️🤖
arXiv:2310.10553
arxiv.org/abs/2310.10553
Michael Bowling retweeted
Today at #ICML2023, I'll be presenting our work on Settling the Reward Hypothesis.
proceedings.mlr.press/v202/b…
Come by our poster and attend the oral presentation to learn about when goals can be expressed as Markov rewards! Together with @MichaelHBowling, @dabelcs, @wwdabney
Michael Bowling retweeted
We have a new paper that I believe really helps to understand what we mean by "goals":
Settling the Reward Hypothesis (arxiv.org/pdf/2212.10420.pdf), joint w/ John Martin (@jdmartin86), Michael Bowling (@MichaelHBowling), and Will Dabney (@wwdabney)
--> Talk/poster on Tuesday
Michael Bowling retweeted
🎉I'm particularly excited to share this project I worked on under the guidance of @MarlosCMachado 🧙
We ask: what is the *right scaffold* for building temporal abstractions, from the ground up?
Website: sites.google.com/view/dceo/
It will be presented next week at #ICML2023 🏝️
Michael Bowling retweeted
I'm happy to share that our paper has now been accepted in JMLR!
Temporal Abstraction in Reinforcement Learning with the Successor Representation
arxiv.org/abs/2110.05740
w/ @andre_s_barreto, Doina Precup, and @MichaelHBowling. 🧵
Michael Bowling retweeted
📯Delighted to finally share our new paper.📯
Settling the Reward Hypothesis.
Joint work with @MichaelHBowling, @dabelcs, @wwdabney.
arxiv.org/abs/2212.10420
[1 / 8]
Michael Bowling retweeted
This is current work I'm doing with
@jdmartin86 and @MichaelHBowling. You can watch the SlidesLive here: nips.cc/virtual/2022/affinit….
Michael Bowling retweeted
Come checkout our work about learning to prioritize planning updates in model-based RL, appearing at the Workshop on Meta Learning. #NeurIPS2022
Joint work w/ Brad Burega and @MichaelHBowling
Paper: openreview.net/forum?id=uR7e…