Standard RL
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
arXiv:2603.17145v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the...
LC-SAC: Lyapunov-Constrained Soft Actor-Critic via Koopman Operator Theory for Trajectory Tracking and Stabilization
arXiv:2602.04132v4 Announce Type: replace Abstract: Reinforcement Learning (RL) has achieved remarkable success in solving complex sequential decision-making problems. However, its application to safety-critical physical systems remains constrained by the lack of stability guarantees. Standard RL algorithms prioritize reward maximization, often yielding policies that may induce oscillations or unbounded state divergence.
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
arXiv:2605.31388v1 Announce Type: new Abstract: Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as an effective approach for promoting fairness, its applicability remains limited, particularly when constraints must be incorporated. In this paper, we propose a MORL framework that integrates the max-min criterion with explicit constraint satisfaction.
Libra: Efficient Resource Management for Agentic RL Post-Training
arXiv:2606.03077v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that challenge conventional resource-management assumptions. Three fundamental challenges arise.
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
arXiv:2606.01476v1 Announce Type: new Abstract: On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy distribution shift of Supervised Fine-Tuning (SFT) and the sparse credit assignment of Reinforcement Learning (RL). However, standard OPD faces two coupled limitations. First, it requires direct access to the teacher's token-level logits, excluding a broad class of...
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Announce Type: new Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five terminal-agent benchmarks and find 323 (16%) hackable by frontier models given only the task description. This corrupts both leaderboard rankings and RL training signal, yet the standard response is manual and reactive.
RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training
arXiv:2606.04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from scratch and applying RL, SFT, and SFT followed by RL directly to intermediate pre-training checkpoints. We find that RL is effective very early, and often matches the full SFT$\to$RL pipeline early as well.
Policy and World Modeling Co-Training for Language Agents
Announce Type: new Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, yet existing approaches often require separate simulators, extra training stages, or additional inference-time computation. We observe that on-policy RL rollouts already contain the needed signal: each transition pairs an...
The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning
arXiv:2606.07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling and weighting, leading to inefficient compute allocation. We study GRPO by tracking token log-probabilities, group-normalized advantages, and the induced token-level update weights. This reveals three recurring dynamics as training proceeds: (1) confidence inflation,...
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
arXiv:2605.30719v1 Announce Type: new Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.e., when can we replace classical RL algorithms with an LLM? We explore this question by introducing Prompted Policy Optimization (PromptPO), an iterative method that prompts an LLM with Python descriptions of the state space, action space, and reward function, then has it generate and refine executable policies...