arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.
arXiv:2605. 00155v3 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility.
arXiv:2606. 19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model.
BCPPO is a new variant of Proximal Policy Optimization that uses Bachelier-inspired cost‑prediction networks to generate a smooth penalty based on disagreement among critics. The method keeps temporal‑difference learning unchanged, applies a saturation‑aware controller to manage cost penalties, and deploys only the policy network. Across extensive experiments, BCPPO outperforms comparators in achieving higher mean returns while maintaining lower or comparable CVaR in all tested tasks.
arXiv:2606. 19328v1 Announce Type: cross Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design.
arXiv:2606. 19818v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards.
arXiv:2609. 10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications.
The paper introduces CoDRA, a cost-to-disturbance ratio approach for adversarial reinforcement learning that balances controller performance and disturbance exposure without extra penalty terms. CoDRA uses a self‑normalized actor–critic update, scaling value terms by a stop‑gradient normalization constant derived from the current batch. Experiments on MuJoCo pendulum tasks show that CoDRA achieves the lowest cost across a range of forces and masses, outperforming other methods especially on the more challenging InvertedDoublePendulum environment.
arXiv:2402. 06734v2 Announce Type: replace-cross Abstract: We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting.
arXiv:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
The paper introduces Reward Ensemble under Confidence (REC), a probabilistic reward learning framework for preference-based reinforcement learning that models per‑timestep reward uncertainty using an ensemble of distributional reward models. REC incorporates uncertainty into the preference loss and uses model disagreement to drive exploration, achieving 88.4% of shaped‑reward performance on acrobatic quadrotor control versus 55.2% with standard Preference PPO. The authors train policies in simulation and transfer them zero‑shot to real quadrotors, demonstrating complex acrobatic maneuvers learned solely from human preference feedback, and validate REC on a continuous‑control benchmark.