Claude 3 Opus strategically fakes alignment by complying with harmful requests only during simulated training to preserve its preference for refusing them afterward.
mega hub Mixed citations
Proximal Policy Optimization Algorithms
Mixed citation behavior. Most common role is background (52%).
1699
Pith papers citing it
Background
52% of classified citations
abstract
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.
hub tools
citation-role summary
background 155
method 113
baseline 15
dataset 4
citation-polarity summary
claims ledger
- abstract We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more ge
authors
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
GRPO's group-mean baseline assigns identical advantages to all tokens under output-only rewards, inducing gradient sparsity and an intrinsic rank-2 structure proven from the zero-sum constraint and confirmed by SVD on Nemotron-4B gradients.
Negative narrative immersion causes 12-31% drops in LLM moral accuracy and produces structured shifts that appear in downstream applications.
RL agent for online LHC trigger threshold tuning improves in-tolerance intervals by 28-56% on Monte Carlo and real CMS data without fine-tuning.
A reward-free representation learning pipeline for offline PbRL achieves better preference efficiency than standard two-stage baselines by connecting RFRL concepts to preference data.
Dynamic isotropy, quantifying uniform center-of-mass acceleration capability, improves robot performance and enables omnidirectional locomotion, terrain traversal, and failure resilience in a spherical robot design.
AtomComposer uses online RL with multi-composition training to discover up to 10x more valid 3D isomers on unseen chemical formulas than single-composition baselines.
Agent-BRACE improves LLM agent performance on long-horizon partially observable tasks by 5.3-14.5% through a decoupled belief state of verbalized atomic claims with certainty labels that keeps context length constant.
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
ReLibra uses pre-known token-to-expert routing from RL rollouts to perform inter-batch expert reordering and intra-batch replication, delivering up to 1.6x higher throughput than Megatron-LM and 1.2x over oracle-equipped EPLB while staying within 6-10% of an ideal balanced baseline.
Weak-to-strong generalization is nearly inevitable in linear logistic regression for most student-teacher pairs without any model capacity mismatch.
Observation and action delays are formally equivalent in cooperative Dec-POMDPs, yielding identical optimal solutions and enabling zero-shot transfer, though learning dynamics differ due to credit assignment and operational constraints.
A language-game framework enables dialogue with dynamical systems such as GRNs by treating their frozen dynamics as an RL policy core, using an LM to route prompts so the system responds through its own behavior without parameter changes.
RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.
User-turn generation reveals that LLMs' interaction awareness is largely decoupled from task accuracy, remaining near zero in deterministic settings even as accuracy scales to 96.8% on GSM8K.
Derives an exact unbiased policy gradient for RL post-training of diffusion LLMs via entropy-guided step selection and one-step denoising rewards, achieving state-of-the-art results on coding and logical reasoning benchmarks.
A certified gradient-based method for contact-rich manipulation that quantifies smoothing-induced errors via set-valued discrepancies and incorporates them into analytical reachable sets for robust affine feedback policies.
First in-orbit demonstration of a DRL-trained AI satellite attitude controller that performs robust inertial pointing after sim-to-real transfer.
Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
SWE-Gym supplies 2438 executable real-world Python tasks to train SWE agents and verifiers, yielding up to 19% gains and new open-weight SOTA of 32% on SWE-Bench Verified.
BEHAVIOR-1K introduces a benchmark of 1,000 human everyday activities in realistic simulated scenes together with the OMNIGIBSON physics simulator to evaluate embodied AI.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
citing papers explorer
-
Alignment faking in large language models
Claude 3 Opus strategically fakes alignment by complying with harmful requests only during simulated training to preserve its preference for refusing them afterward.
-
Training Software Engineering Agents and Verifiers with SWE-Gym
SWE-Gym supplies 2438 executable real-world Python tasks to train SWE agents and verifiers, yielding up to 19% gains and new open-weight SOTA of 32% on SWE-Bench Verified.
-
BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
BEHAVIOR-1K introduces a benchmark of 1,000 human everyday activities in realistic simulated scenes together with the OMNIGIBSON physics simulator to evaluate embodied AI.
-
ORPO: Monolithic Preference Optimization without Reference Model
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
-
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
EARL-BO uses RL with an Attention-DeepSets encoder and end-to-end on-policy multi-task fine-tuning to approximate near-optimal multi-step lookahead policies for high-dimensional black-box optimization.
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
KTO: Model Alignment as Prospect Theoretic Optimization
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
-
Self-Rewarding Language Models
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
-
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
HuatuoGPT-o1 achieves superior medical complex reasoning by using a verifier to curate reasoning trajectories for fine-tuning and then applying RL with verifier-based rewards.
-
RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields
A deep RL vulnerability-prediction policy trained in semantic embedding space finds up to 23% more unique robot manipulation failures than vision-language baselines and enables more efficient fine-tuning.
-
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
-
The Hive Mind is a Single Reinforcement Learning Agent
Bee hive mind from weighted voter imitation equals a single RL agent using a new multi-armed bandit rule called Maynard-Cross Learning.
-
HybridFlow: A Flexible and Efficient RLHF Framework
HybridFlow combines single- and multi-controller paradigms with a 3D-HybridEngine to deliver 1.53x to 20.57x higher throughput for various RLHF algorithms compared to prior systems.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots
A single learned controller called MHC enables real humanoid robots to execute diverse whole-body behaviors from multi-modal inputs via masked target trajectories.
-
Proximal Policy Distillation
PPD integrates PPO into policy distillation so the student collects and uses its own rewards, yielding better sample efficiency and robustness than standard student-distill or teacher-distill on ATARI, Mujoco, and Procgen tasks.
-
DataComp-LM: In search of the next generation of training sets for language models
DCLM-Baseline dataset lets a 7B model reach 64% 5-shot MMLU accuracy after 2.6T tokens, beating prior open-data models by 6.6 points on MMLU with 40% less compute.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Seed-TTS models produce speech matching human naturalness and speaker similarity, with added controllability via self-distillation and reinforcement learning.
-
A Survey on Vision-Language-Action Models for Embodied AI
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
-
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.
-
Continual Domain Randomization
Continual Domain Randomization trains RL policies sequentially on randomization parameter subsets with continual learning to achieve robust sim-to-real transfer in robotic reaching and grasping.
-
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.
-
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeekMath 7B reaches 51.7% on MATH via continued pretraining on curated web math data and Group Relative Policy Optimization.
-
AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
AutoSculpt models DNNs as graphs, embeds pruning patterns, and uses deep reinforcement learning to reach up to 90% pruning and 18% better FLOPs reduction than baselines on ResNet, MobileNet, VGG, and Vision Transformers.
-
Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution
HRT is a bi-level RL framework with a sparse high-level controller for asset direction selection from signals and a risk-aware low-level controller for weight adjustments, reporting Sharpe 1.24 and turnover 0.090 on 2020-2023 Nasdaq data.
-
Molecular Quantum Control Algorithm Design by Reinforcement Learning
Reinforcement learning designs quantum-logic pulse sequences to prepare H3O+ (130 states) and CaH+ molecular ions in pure states from thermal populations.
-
Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning
A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.
-
Fast State Stabilization using Deep Reinforcement Learning for Measurement-based Quantum Feedback Control
Deep reinforcement learning applied to measurement-based quantum feedback control achieves faster stabilization of random initial states to target entangled states in two- and three-qubit systems than Lyapunov feedback or alternative DRL reward designs.
-
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.
-
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
InternLM-XComposer-2.5 is a 7B vision-language model supporting up to 96K context that reaches GPT-4V-level performance on image, video, and multi-turn tasks and adds LoRA-driven text-image composition capabilities.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
-
InternLM2 Technical Report
InternLM2 is a new open-source LLM that outperforms prior versions on 30 benchmarks and long-context tasks through scaled pre-training to 32k tokens and a conditional online RLHF alignment strategy.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
-
Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning
A centralized HRL planner with HTAN, multi-stage curricula, and counterfactual baseline scales multi-robot task planning to 200 robots and 1000 racks on unlearned maps in RMFS.
-
A Survey on LLM-as-a-Judge
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Data-centric filtering yields an 80K preference dataset and reward models that lead RewardBench while boosting other top entries.
-
Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning
RL simulations find explicit action guidance in instructions and a specific ordering curriculum improve number composition learning and generalization.
-
SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration
SmileyLlama is an LLM transformed via SFT and DPO to generate valid novel drug-like molecules with user-specified properties and optimized 3D conformations for high binding affinity.
-
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
STILL-2 uses imitation of distilled long-form thoughts, multi-rollout exploration on difficult problems, and iterative self-improvement of the dataset to train reasoning models that reach competitive performance on three challenging benchmarks.
-
Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control Framework
TriCoD is a cooperative decision-making framework using twin-world deduction and adaptive switching between DRL and model-driven methods to enable safe, dynamic AV platooning in hybrid traffic.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
- Inpatient Overflow Management with Proximal Policy Optimization