Sasha Abramowitz
@sash-4.bsky.social
Research engineer at InstaDeep working on multi-agent RL
🔬In a benchmark across 45 diverse tasks (the largest in the literature), Sable substantially outperformed existing methods, ranking best 11 times more often than previous SOTA methods.
(4/N)
(4/N)
July 14, 2025 at 3:42 PM
🔬In a benchmark across 45 diverse tasks (the largest in the literature), Sable substantially outperformed existing methods, ranking best 11 times more often than previous SOTA methods.
(4/N)
(4/N)
💪 Our solution? Sable adapts the retention mechanism from Retentive Networks (RetNets) and achieves centralised learning advantages without the associated drawbacks. This allows for efficient, long-term memory and impressive scalability.
(3/N)
(3/N)
July 14, 2025 at 3:41 PM
💪 Our solution? Sable adapts the retention mechanism from Retentive Networks (RetNets) and achieves centralised learning advantages without the associated drawbacks. This allows for efficient, long-term memory and impressive scalability.
(3/N)
(3/N)
🚨 Thrilled to share our #ICML2025 paper: "Sable: a Performant, Efficient and Scalable Sequence Model for MARL"!
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
July 14, 2025 at 3:40 PM
🚨 Thrilled to share our #ICML2025 paper: "Sable: a Performant, Efficient and Scalable Sequence Model for MARL"!
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)
We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks.
(1/N)