I make the case why people iteratively training any model should learn some core concerns of reinforcement learning.
6
Choices, risks, and reward reporting. Recommendations for how to integrate RL systems with society.
1
A tour of control theory, multi-agent RL, and hierarchical learning.
2
Industry labs power up their robot learning research with parallelization!
2
How RL is starting to be used by industry and how RL is heading to a framing more suited for industrial scales.
4
Multi-agent scenarios make reward maximization a risk. Discussing when, rather than if, we should believe in the Reward Hypothesis.
2
How simulator exploitation, a dual of over-optimization, in AI is the canary in the coal mine for what negative implications could come from…
4
1
I don’t even like the idea of flying delivery drones, but that will be all we have.
3
1
See all

Democratizing Automation