Methods › General › Meta-Learning Algorithms › MeRL

Meta Reward Learning

MeRL

10 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Meta Reward Learning (MeRL) is a meta-learning method for the problem of learning from sparse and underspecified rewards. For example, an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. The key insight of MeRL in dealing with underspecified rewards is that spurious trajectories and programs that achieve accidental success are detrimental to the agent's generalization performance. For example, an agent might be able to solve a specific instance of the maze problem above. However, if it learns to perform spurious actions during training, it is likely to fail when provided with unseen instructions. To mitigate this issue, MeRL optimizes a more refined auxiliary reward function, which can differentiate between accidental and purposeful success based on features of action trajectories. The auxiliary reward is optimized by maximizing the trained agent's performance on a hold-out validation set via meta learning.

Source: Learning to Generalize from Sparse and Underspecified RewardsSee Code · google-research/google-research

Papers archive 2025-07-28

10 shown of 10, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 30 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Action Segmentation3
Generative Adversarial Network3
Reinforcement Learning2
Reinforcement Learning (RL)2
Representation Learning2
Segmentation2
reinforcement-learning2
Action Classification1
Action Detection1
Activity Detection1
Activity Recognition1
Bayesian Optimization1
Clinical Knowledge1
Continuous Control1
Contrastive Learning1
Descriptive1
Diagnostic1
ECG Classification1
Fine-Grained Action Detection1
ISAC1

Usage over time archive 2025-07-28

Papers per year tagged with MeRL: 2019 to 2025, peak 6 6 0 2019: 6 papers 2019 2020: 1 paper 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 0 papers 2023 2024: 2 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (10 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Meta-Learning Algorithms

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections