Reinforcement Learning

This paper demonstrates that a complex deep reinforcement learning policy for power grid control can be successfully distilled into a lightweight, auditable decision tree and random forest surrogate t…

The paper proposes a two-timescale governance framework using a multi-agent LLM to safely update and guide RL agents for SDN-IoT defense, significantly improving performance and stability under advers…

The paper proposes a privacy-aware machine unlearning framework using SISA training to efficiently remove the influence of specific training data from RL-based ransomware detectors with minimal perfor…

The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are in…

The paper introduces AgenticRL, a self-refining reinforcement learning framework that uses a multimodal GPT agent to automatically design, refine, and deploy reward functions for complex UAV navigatio…

The paper develops and validates a novel Deep Reinforcement Learning (DRL) framework to enhance pair trading in volatile cryptocurrency markets, demonstrating statistically significant outperformance…

This paper introduces Numca and Hista, two novel techniques that significantly improve state value estimation for LLM reinforcement learning, addressing the instability of standard critic approaches.

The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent ga…

The paper introduces ReMax, a novel objective function that naturally encourages stochastic exploration in policy gradient reinforcement learning by evaluating expected maximum returns over multiple s…

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

This paper introduces CHERRL, a controllable hacking environment for rubric-based reinforcement learning to study and mitigate reward hacking.

The paper proposes a novel RL framework that naturally induces diverse agent behavior by reformulating the objective to treat the reward as a distribution over functions, making diversity a rational r…

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…

ESPO is a novel reinforcement learning algorithm that detects trajectory failure in large language models and terminates rollouts early, significantly improving performance on mathematical reasoning b…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment…

The paper introduces a diagnostic-driven iterative refinement process for improving LLM-generated reward functions in sparse, structured reinforcement learning tasks, significantly boosting agent perf…

The paper introduces Aethelgard, a novel four-layer adaptive governance framework that enforces least privilege by learning the minimum necessary capabilities for autonomous AI agents based on their i…

The paper proposes a coherent inverse reinforcement learning (IRL) method to improve large behavior models for robotic control, achieving superior sample efficiency and performance on complex sparse m…

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…