Video
Unknown · 0:00
Joseph Suarez's main argument is that reinforcement learning (RL) didn't stall because its algorithms hit a wall. It stalled because academia rewarded new algorithms and sample efficiency, and treated engineering and...
Unknown · 0:00
Joseph Suarez's main argument is that reinforcement learning (RL) didn't stall because its algorithms hit a wall. It stalled because academia rewarded new algorithms and sample efficiency, and treated engineering and...
Redirecting...