arXiv:2608.24488v1 Announce Type: new Abstract: Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured chan...
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
The paper critiques the use of pass@$k$ as a sole metric for evaluating reinforcement‑learning post‑training on language models, showing that it ignores diversity in model outputs. Experiments on Qwen2.5‑1.5B‑Instruct trained with Group Relative Policy Optimization (GRPO) and rejection‑sampling fine‑tuning (RFT) reveal that these methods shift token‑level, answer‑level, and unique‑answer diversity in opposite directions, yet pass@$k$ fails to capture these differences. Even when restricting to verifier‑correct completions, diversity gaps persist, and pass@$k$ does not consistently identify the better performing arm on hard problem subsets, indicating that the metric can mask true capability changes.
arXiv:2609.39634v1 Announce Type: cross Abstract: Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribu...
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
The paper critiques the common reinforcement‑learning approach of sampling tool subsets when the full set of tools is enumerable, showing that sampling leads to degraded policy estimates and increased reward sparsity in genomic reasoning tasks. It proposes Full‑Group Policy Optimization (FGPO), which evaluates every tool subset and precomputes rewards in a table, thereby eliminating the need for frozen‑reasoner calls during training. Experiments across five frozen reasoners and three genomic benchmarks demonstrate that FGPO consistently outperforms GRPO, improving average scores by 6.75 points and reducing the number of invoked tools per question.
arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.
Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatched in specialist sc...
The paper investigates why world models used for planning can misjudge returns despite producing visually accurate rollouts. By replacing imagined transitions with real ones at key event steps—where rewards are earned or episodes end—the authors show that correcting these few transitions eliminates about 70% of return errors, outperforming corrections based on high visual error metrics. Across 44 Atari-100k model–collection pairs, event-based patches significantly improve plan ranking, revealing a structured pattern of remaining errors that can guide further repairs.
arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.
arXiv:2511. 22581v5 Announce Type: replace Abstract: We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initialization, to the same joint policy, and that this joint policy is equivariant w.