Dylan Cope
@dylancope.bsky.social
Researching multi-agent RL, emergent communication, and evolutionary computation.
Postdoc at FLAIR Oxford. PhD from Safe and Trusted AI CDT @ KCL/Imperial. Previously visiting researcher at CHAI U.C. Berkeley.
dylancope.com
he/him
London 🇬🇧
Postdoc at FLAIR Oxford. PhD from Safe and Trusted AI CDT @ KCL/Imperial. Previously visiting researcher at CHAI U.C. Berkeley.
dylancope.com
he/him
London 🇬🇧
When people are interested in learning about how to train agents to communicate (emergent communication), I always recommend this paper as a first read: dl.acm.org/doi/10.5555/...
Attached meme summarises the main pitfall to be wary of!
Attached meme summarises the main pitfall to be wary of!
November 25, 2024 at 1:43 PM
When people are interested in learning about how to train agents to communicate (emergent communication), I always recommend this paper as a first read: dl.acm.org/doi/10.5555/...
Attached meme summarises the main pitfall to be wary of!
Attached meme summarises the main pitfall to be wary of!
Post a non-religious photo you think of as holy.
November 21, 2024 at 5:20 PM
Post a non-religious photo you think of as holy.
Managed to stump it with a drop that relies on correcting your balance with the wall. Wasn't too hard for me to get it but the agents don't get it!
November 20, 2024 at 12:37 PM
Managed to stump it with a drop that relies on correcting your balance with the wall. Wasn't too hard for me to get it but the agents don't get it!