arXiv:2610.35865v1 Announce Type: new Abstract: Evolution strategies (ES) update a model by sampling a population of perturbed copies, scoring each one, and moving in the reward-weighted direction of...
arXiv:2602. 02572v2 Announce Type: replace-cross Abstract: Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy.
The paper investigates emergent misalignment in reward models, showing that fine‑tuning reward models to prefer harmful content in a single domain (medical or financial) causes the preference to generalize to seven other domains. The authors fine‑tune two state‑of‑the‑art reward models—Skywork‑Reward‑V2‑Llama‑3.1‑8B and Skywork‑Reward‑V2‑Qwen3‑8B—and find that the models still perform well on the standard RewardBench 2 evaluation while exhibiting a preference for harm. Mechanistically, the study identifies two key changes in the reward models’ representations: a geometric compression that reduces the angle between sound and harmful responses, and a content‑specific rotation that aligns harmful representations more closely with the scalar head, thereby increasing their reward score.
arXiv:2607. 18300v1 Announce Type: cross Abstract: We extend Incentive Compatible Exploration beyond the Bayesian full-information setting of Kremer et al.
The paper investigates how curriculum learning affects reinforcement learning in a minimal policy learning model. It shows that when rewards are dense, curricula offer only marginal benefits, but when rewards are sparse, curricula become essential for learning to occur. The study also highlights that competing objectives—minimizing effort versus maximizing reward—create distinct optima that curricula can help navigate by reducing reward sparsity and reshaping the reward landscape.
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this setting either require c...
The paper introduces a computationally efficient algorithm for infinite-horizon average-reward constrained Markov decision processes (CMDPs) under weak communication. It achieves a high-probability regret and cumulative constraint violation of ×O(√T) in the tabular setting, matching optimal dependence up to logarithmic factors. The method augments the state with cumulative constraint violation, reshapes rewards using a Huber potential, and applies finite-horizon approximation with optimistic value iteration to maintain bounded per-step rewards.
arXiv:2601. 21523v2 Announce Type: replace Abstract: To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting.
ReCAST is a method for assigning credit to multiple rewards during diffusion model training by using a reward-by-timestep weight matrix that respects user-specified reward budgets while ensuring equal total weight per denoising step. It allocates weight based on each reward’s informativeness, measured by its Rényi discriminability gain at each step, allowing rewards to contribute more when they are most informative. Experiments on SD3.5‑Medium with two four‑reward settings show that ReCAST improves or matches training rewards, enhances held‑out judges, and is preferred by an independent LLM‑as‑a‑Judge, indicating generalizable benefits.
arXiv:2511. 02577v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is widely regarded as one of the most successful deep reinforcement learning algorithms, known for its robustness and effectiveness across a range of problems.
arXiv:2609.36820v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing...
arXiv:2608. 03092v1 Announce Type: cross Abstract: We aim to improve model performance in multi-reward reinforcement learning training process.