Josh McClellan
@joshmcclellan.bsky.social
I study generalization for reinforcement learning
Fwiw Tesla isn't the first to build an LFG plant in the US.
Looks like LGES started production in May. (I think it's a joint venture with GM)
Tesla just has such a huge marketing megaphone so you hear about them more
Looks like LGES started production in May. (I think it's a joint venture with GM)
Tesla just has such a huge marketing megaphone so you hear about them more
July 2, 2025 at 11:00 PM
Fwiw Tesla isn't the first to build an LFG plant in the US.
Looks like LGES started production in May. (I think it's a joint venture with GM)
Tesla just has such a huge marketing megaphone so you hear about them more
Looks like LGES started production in May. (I think it's a joint venture with GM)
Tesla just has such a huge marketing megaphone so you hear about them more
Tesla has a lot more cash (big margins in 2020-2024, can sell stock etc), and got a head start on batteries.
But the other US automakers are working on this.
GM has a joint LFP plant set for 2027.
LGES already opened an LFG plant in US
GM ultium platform is also schnazzy.
But the other US automakers are working on this.
GM has a joint LFP plant set for 2027.
LGES already opened an LFG plant in US
GM ultium platform is also schnazzy.
July 2, 2025 at 10:56 PM
Tesla has a lot more cash (big margins in 2020-2024, can sell stock etc), and got a head start on batteries.
But the other US automakers are working on this.
GM has a joint LFP plant set for 2027.
LGES already opened an LFG plant in US
GM ultium platform is also schnazzy.
But the other US automakers are working on this.
GM has a joint LFP plant set for 2027.
LGES already opened an LFG plant in US
GM ultium platform is also schnazzy.
I heard someone once say that Tesla's best selling product is its stock lol.
April 13, 2025 at 5:20 PM
I heard someone once say that Tesla's best selling product is its stock lol.
A Song of Ice and Fire! I especially love the audiobooks
A couple of the early Witcher books are good too
A couple of the early Witcher books are good too
December 26, 2024 at 3:46 PM
A Song of Ice and Fire! I especially love the audiobooks
A couple of the early Witcher books are good too
A couple of the early Witcher books are good too
This robustness stems directly from its symmetry guarantees, allowing it to lose less performance when adapting to new scenarios.
If you'll be at Neurips come visit our poster next week to learn more and discuss the exciting future of MARL!
If you'll be at Neurips come visit our poster next week to learn more and discuss the exciting future of MARL!
December 6, 2024 at 3:20 PM
This robustness stems directly from its symmetry guarantees, allowing it to lose less performance when adapting to new scenarios.
If you'll be at Neurips come visit our poster next week to learn more and discuss the exciting future of MARL!
If you'll be at Neurips come visit our poster next week to learn more and discuss the exciting future of MARL!
E2GN2 also shines when it comes to generalization. In tests where agents are trained on one SMACv2 scenario and then tested on a different one, E2GN2 demonstrates up to 5x greater performance than standard approaches.
December 6, 2024 at 3:20 PM
E2GN2 also shines when it comes to generalization. In tests where agents are trained on one SMACv2 scenario and then tested on a different one, E2GN2 demonstrates up to 5x greater performance than standard approaches.
How much better is E2GN2? We see a remarkable 2x-5x improvement in sample efficiency over standard graph neural networks in the challenging SMACv2 benchmark. This means faster training times, leading to more rapid progress in MARL research.
December 6, 2024 at 3:20 PM
How much better is E2GN2? We see a remarkable 2x-5x improvement in sample efficiency over standard graph neural networks in the challenging SMACv2 benchmark. This means faster training times, leading to more rapid progress in MARL research.
Imagine teaching a robot to play soccer. If it learns to pass the ball to the right, it should easily grasp how to pass to the left due to the inherent symmetries. E2GN2 bakes this concept of symmetry into the network architecture, allowing agents to learn more effectively
December 6, 2024 at 3:20 PM
Imagine teaching a robot to play soccer. If it learns to pass the ball to the right, it should easily grasp how to pass to the left due to the inherent symmetries. E2GN2 bakes this concept of symmetry into the network architecture, allowing agents to learn more effectively
Traditional neural networks (ie MLPs, GNNs) learn input/output relationships with few constraints, structure, or priors on the policies learned. These generic architectures lack a strong inductive bias making them inefficient in terms of the training samples required.
December 6, 2024 at 3:20 PM
Traditional neural networks (ie MLPs, GNNs) learn input/output relationships with few constraints, structure, or priors on the policies learned. These generic architectures lack a strong inductive bias making them inefficient in terms of the training samples required.
Our work focuses on addressing the challenges of sample inefficiency and poor generalization in Multi-Agent Reinforcement Learning (MARL), a crucial area of AI research with applications in robotics, game playing, and more.
December 6, 2024 at 3:20 PM
Our work focuses on addressing the challenges of sample inefficiency and poor generalization in Multi-Agent Reinforcement Learning (MARL), a crucial area of AI research with applications in robotics, game playing, and more.