Corina Catarau
@corinacatarau.bsky.social
PhD student in AI | Functional creativity | Creativity in artificial agents | Representation learning | RL | ML engineer
Finalising my PhD this year has been one of the most rewarding experiences. I still remember walking into Esther’s office five years ago with just an idea, and I couldn’t be more grateful for all the guidance and support from her and Eduardo throughout this journey. Thank you!
Congratulations to @corinacatarau.bsky.social for passing her viva with flying colours, and for, in the words of the examiners, a courageous and very original approach to address reinforcement learning agents' generalisation.
Bravo, Corina. I am very proud of you!
Bravo, Corina. I am very proud of you!
October 5, 2025 at 7:19 AM
Finalising my PhD this year has been one of the most rewarding experiences. I still remember walking into Esther’s office five years ago with just an idea, and I couldn’t be more grateful for all the guidance and support from her and Eduardo throughout this journey. Thank you!
Reposted by Corina Catarau
New preprint with @corinacatarau.bsky.social and
@ealonso.bsky.social from @citai.bsky.social:
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
arxiv.org/abs/2503.13194
@ealonso.bsky.social from @citai.bsky.social:
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
arxiv.org/abs/2503.13194
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focuse...
arxiv.org
March 18, 2025 at 2:52 PM
New preprint with @corinacatarau.bsky.social and
@ealonso.bsky.social from @citai.bsky.social:
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
arxiv.org/abs/2503.13194
@ealonso.bsky.social from @citai.bsky.social:
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
arxiv.org/abs/2503.13194