Honglak Lee, Sergey Levine, Esteban Real, Quoc Le, Daiyi Peng, John Co-Reyes, Yingjie Miao, Aleksandra Faust
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.
We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm. Bootstrapped from DQN, we highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games. The analysis of the learned algorithm behavior shows resemblance to recently proposed RL algorithms that address overestimation in value-based methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2101.03958")
get_code_for_paper("2101.03958")
have("2101.03958")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2101.03958.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2101.03958)
Connect an agent — have() is free.