David Silver, Satinder Singh, Tom Zahavy, Sebastian Flennerhag, Yannick Schroecker, Deepmind Hado Van Hasselt
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Meta-learning empowers artificial intelligence to increase its efficiency by learning how to learn. Unlocking this potential involves overcoming a challenging metaoptimisation problem. We propose an algorithm that tackles this problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the metalearner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. Focusing on meta-learning with gradients, we establish conditions that guarantee performance improvements and show that the metric can control meta-optimisation. Meanwhile, the bootstrapping mechanism can extend the effective meta-learning horizon without requiring backpropagation through all updates. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark and demonstrate that it yields both performance and efficiency gains in multi-task meta-learning. Finally, we explore how bootstrapping opens up new possibilities and find that it can meta-learn efficient exploration in an ε-greedy Q-learning agent-without backpropagating through the update rule.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.04504")
get_code_for_paper("2109.04504")
have("2109.04504")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.04504.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.04504)
Connect an agent — have() is free.