X · @cwolferesearch
· X / Twitter
Another point to consider that drives home the importance / complexity of environment management: If we assume one environment per rollout in RL, we c…
Another point to consider that drives home the importance / complexity of environment management:If we assume one environment per rollout in RL, we can have O(100) environments running concurrently for each policy update (assuming only one RL run at a time). But, frontier evals today often use multiple containers per t