Tag
This paper introduces a meta-multi-agent reinforcement learning (meta-MARL) framework that formulates MARL problems as Markov games and defines a new solution concept, meta-NE, with proven equivalence to stationary points of a gradient-play-based algorithm, demonstrating faster adaptation on autonomous-driving tasks compared to pretrained MARL baselines.
The paper introduces the Free Inference dimension, a combinatorial complexity measure for zero-collision navigation in meta-reinforcement learning under hypothesis mixtures, proving its relationship with VC-dimension and generalization bounds.
A researcher highlights that meta-RL is a promising direction for training LLM agents, reframing agent training as a cross-episode meta-RL problem to enable active exploration and trial-and-error adaptation.
A new research paper reframes LLM agent training as a cross-episode Meta-RL problem, using critic-free policy gradients to enable in-context adaptation without gradient updates. The LAMER framework improves test-time performance by 11-19% over standard RL baselines on long-horizon tasks and generalizes better to unseen environments.
This survey examines in-context reinforcement learning (ICRL) under non-stationary environments, where a pretrained decision model adapts through accumulated context without parameter updates. It organizes the literature around what changes, how it unfolds, and how observable it is, and identifies research gaps such as stale-context stress tests and adaptive forgetting.