37 stories tagged Reinforcement Learning · page 2 of 2
Researchers have developed a new approach called Adaptive Entropy Modulation (AEM) to improve how AI agents learn complex, multi-step tasks. This could make AI assistants better at handling long conversations or tasks with many steps.
A new paper introduces metrics to evaluate the effectiveness of reinforcement learning from verifiable rewards (RLVR) in language models. The study finds that reasoning chains may not always be causally important or sufficient for verifying answers.
Researchers introduce SAVOIR, a new method for training language agents in social intelligence using Shapley values. This approach improves reward attribution in multi-turn dialogues, addressing a key challenge in reinforcement learning.
Researchers introduce a novel framework that integrates large language models (LLMs) with Random Forests (RF) through reinforcement learning. This method enables iterative feedback between gradient-based and non-differentiable models, enhancing predictive performance.
Ecom-RLVE is a new open-source framework designed to create verifiable and adaptive environments for e-commerce conversational agents. It aims to enhance the reliability and performance of AI-driven customer interactions.
Researchers propose Self-Distillation Zero (SD-Zero), a method that improves training efficiency by converting binary rewards into dense supervision. This approach outperforms traditional reinforcement learning methods in verifiable settings.
Researchers propose a method to improve factuality in long-form LLM outputs by calibrating reasoning confidence. This approach reduces overconfident incorrect claims without post-hoc revision.
Researchers introduce StaRPO, a reinforcement learning framework that improves logical consistency in language models. It augments traditional RL with stability constraints to capture internal reasoning structures.
Researchers introduce Sequence-Level PPO (SPPO), a new method to improve reasoning in LLMs by addressing temporal credit assignment and memory costs. SPPO enhances stability and efficiency over traditional PPO approaches.
A new paper introduces a mathematical framework for how environments can act as memory for agents in reinforcement learning. Experiments show that spatial paths can reduce the information needed to represent history.
Researchers introduce RAMP, a novel approach combining reinforcement learning and action model learning for numeric domains. This method enables online learning directly from environment interactions, eliminating the need for pre-recorded expert traces.
Researchers introduce AGD-MBRL, a new method that uses advantage estimates to guide diffusion models in reinforcement learning, reducing compounding errors. This approach outperforms traditional policy-only and reward-based guides.
Researchers propose a new method for resource-aware knowledge distillation in multi-agent reinforcement learning (MARL). The approach addresses the challenges of deploying expert policies on edge devices by focusing on coordination structure and heterogeneous agent capabilities.