Methods › General › Meta-Learning Algorithms › MeRL
Meta Reward Learning
MeRL
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.
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.
-
Joint Antenna Position and Transmit Power Optimization for Pinching Antenna-Assisted ISAC Systems 17 Mar 2025 · 0 repositories · arXiv:2503.12872
-
Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement 11 Mar 2024 · 2 repositories · arXiv:2403.06659Syntology ran 8 of 12 samples · 4 unverified
-
Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning 9 Feb 2024 · 0 repositories · arXiv:2402.06135
-
Hierarchical Attention Network for Action Segmentation 7 May 2020 · 0 repositories · arXiv:2005.03209
-
MERL: Multi-Head Reinforcement Learning 26 Sep 2019 · 0 repositories · arXiv:1909.11939
-
Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation 20 Sep 2019 · 0 repositories · arXiv:1909.09283
-
Fine-grained Action Segmentation using the Semi-Supervised Action GAN 20 Sep 2019 · 0 repositories · arXiv:1909.09269
-
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination 18 Jun 2019 · 0 repositories · arXiv:1906.07315
-
Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection 11 May 2019 · 0 repositories · arXiv:1905.04430
-
Learning to Generalize from Sparse and Underspecified Rewards 19 Feb 2019 · 1 repository · arXiv:1902.07198
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.
Usage over time archive 2025-07-28
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
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