Gautier Hamon
@hamongautier.bsky.social
📤 54
📥 80
📝 11
PhD student at INRIA Flowers team. MVA master reytuag.github.io/gautier-hamon/
pinned post!
1/⚡️Looking for a fast and simple Transformer baseline for your RL environment in JAX ? Sharing my implementation of transformerXL-PPO:
github.com/Reytuag/tran...
The implementation is the first to attain the 3rd floor and obtain advanced achievements in the challenging Craftax
loading . . .
10 months ago
1
3
1
reposted by
Gautier Hamon
Marko Cvjetko
6 months ago
Complex cell-like structures in Flow Lenia
loading . . .
0
8
2
reposted by
Gautier Hamon
6 months ago
🚀 Introducing 🧭MAGELLAN—our new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.🌍✨Learn more: 🔗
arxiv.org/abs/2502.07709
#OpenEndedLearning
#LLM
#RL
loading . . .
MAGELLAN: Metacognitive predictions of learning progress guide...
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is achieved by LLM...
https://arxiv.org/abs/2502.07709v2
1
9
7
reposted by
Gautier Hamon
cedric
10 months ago
we are recruiting interns for a few projects with @pyoudeyer in bordeaux > studying llm-mediated cultural evolution with @nisioti_eleni @Jeremy__Perez > balancing exploration and exploitation with autotelic rl with @ClementRomac details and links in 🧵 please share!
1
6
6
1/⚡️Looking for a fast and simple Transformer baseline for your RL environment in JAX ? Sharing my implementation of transformerXL-PPO:
github.com/Reytuag/tran...
The implementation is the first to attain the 3rd floor and obtain advanced achievements in the challenging Craftax
loading . . .
10 months ago
1
3
1
Putting some Flow Lenia here too
loading . . .
10 months ago
1
4
1
reposted by
Gautier Hamon
Tim Rocktäschel
10 months ago
Now that
@jeffclune.bsky.social
and
@joelbot3000.bsky.social
are here, time for an Open-Endedness starter pack.
go.bsky.app/MdVxrtD
add a skeleton here at some point
16
105
37
reposted by
Gautier Hamon
Nicolas Yax
10 months ago
🚨New preprint🚨 When testing LLMs with questions, how can we know they did not see the answer in their training? In this new paper we propose a simple out of the box and fast method to spot contamination on short texts with
@stepalminteri.bsky.social
and Pierre-Yves Oudeyer !
1
8
4
you reached the end!!
feeds!
log in