arxiv:2406.04144
Pietro Mazzaglia
mazpie
·
AI & ML interests
Reinforcement learning - Robot learning - World models
Recent Activity
upvoted a paper about 10 hours ago
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck upvoted a paper 2 months ago
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels updated a dataset over 1 year ago
mazpie/genrl_datasetsOrganizations
None yet
