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%).
1840
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.
Machine learning discovers a tube-seeding strategy for IBP reduction of Feynman integrals that scales linearly with numerator power, demonstrated on rank-20 2-loop 5-point integrals.
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.
citing papers explorer
-
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment
ETS performs training-free RL alignment for language models by energy-guided test-time scaling with Monte Carlo energy estimation and importance sampling acceleration.
-
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
-
LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
LERL combines an LLM high-level planner for diverse semantic categories with a low-level RL policy for item selection to improve long-term user satisfaction and reduce content homogeneity in interactive recommenders.
-
Deep Reinforcement Learning for Hybrid RIS Assisted MIMO Communications
A DRL agent learns a direct mapping from channel state information to near-optimal beamforming and hybrid RIS configurations, reaching 95% of the spectral efficiency of alternating optimization at far lower runtime complexity.
-
The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
TGR performs manifold-informed latent foresight search to boost trajectory coverage in long-context reasoning tasks by up to 13 AUC points with minimal overhead.
-
Deep Reinforcement Learning-Based Dynamic Resource Allocation in Cell-Free Massive MIMO
DRL learns antenna activation ratio and power coefficients to optimize energy efficiency in cell-free massive MIMO, achieving 50% EE gain and 3350x speedup over sequential convex approximation.
-
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
SFT and RL cannot be decoupled in LLM post-training because each step increases the loss or lowers the reward of the prior step under KL and PL analyses.
-
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
GDPO decouples per-reward normalization in multi-reward RL to avoid advantage collapse and improve convergence over GRPO on tool-calling, math, and coding tasks.
-
The Illusion of Insight in Reasoning Models
Mid-reasoning shifts in reasoning models are rare symptoms of unstable inference that seldom improve accuracy and do not reflect intrinsic self-correction.
-
Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
GLiBRL uses GLMs with learnable basis functions for exact Bayesian inference in deep BRL, derives a closed-form link between L2 task distances and kernel task similarity, and reports up to 1.8x gains over prior meta-RL on MuJoCo and MetaWorld.
-
DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation
DIAL uses iterative adversarial learning to restore lexical diversity in user simulators and achieve strong correlation with real failure rates while keeping low divergence in failure mode distributions for mental health dialogues.
-
Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments
Pseudo-expert regularized offline RL reduces collisions and improves route completion for camera-based driving models trained on fixed simulator datasets from nuScenes.
-
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
An RL-trained lightweight agent uses MLLM perceptual rewards to perform efficient label-free image restoration, matching SOTA on full-reference metrics and surpassing prior work on no-reference metrics.
-
ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
ImagineNav++ achieves SOTA mapless visual navigation by prompting VLMs to select imagined future views generated from a human-preference-distilled module and maintained via selective foveation memory.
-
Image Diffusion Preview with Consistency Solver
ConsistencySolver enables high-quality low-step diffusion previews by adapting general linear multistep methods into a lightweight RL-optimized solver, matching multistep DPM-Solver FID with 47% fewer steps and cutting user interaction time by nearly 50%.
-
Differentiable Evolutionary Reinforcement Learning
DERL is a differentiable bi-level method that evolves optimal reward structures for RL policies by composing atomic primitives and using meta-gradients from validation performance.
-
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Entropy Ratio Clipping introduces a global entropy-ratio constraint that stabilizes RL policy updates in LLM post-training beyond local PPO clipping.
-
Hierarchical Reinforcement Learning for the Dynamic VNE with Alternatives Problem
HRL-VNEAP applies hierarchical RL to dynamic VNE with alternative topologies and reports up to 20.7% higher acceptance ratio than strong baselines on realistic networks.
-
CARL: Criticality-Aware Agentic Reinforcement Learning
CARL improves long-horizon agentic RL by using entropy as a proxy to identify critical states and selectively updating only on high-criticality actions, yielding stronger performance and efficiency.
-
When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTS
Diffusion models exhibit a structural limitation when generating samples on low-dimensional feasible regions for constrained tasks, and sequential autoregressive generation using RL and MCTS improves constraint satisfaction.
-
Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.
-
Sparse shepherding control of large-scale multi-agent systems via Reinforcement Learning
Reinforcement learning with adaptive compensation achieves sparse control of multi-agent system densities via hybrid ODE-PDE modeling.
-
CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
CropVLM uses reinforcement learning to learn image zooming policies that boost fine-grained perception in VLMs on out-of-domain high-resolution tasks without labeled boxes, synthetic data, or VLM changes.
-
Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning
A periodically asynchronous on-policy RL system for LLM post-training achieves up to 3x throughput gains by separating inference and training with periodic policy synchronization and a tri-model architecture.
-
Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
DIBA detects membership of prompts in RLVR training by measuring reward success changes and policy behavioral drift between pre- and post-RLVR model checkpoints.
-
Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning
A multi-stage RL curriculum produces a unified whole-body controller enabling humanoid robots to sustain badminton rallies in simulation and return shuttles at up to 19.1 m/s in real hardware, with both EKF-based and prediction-free variants.
-
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
Scaling motion tracking models along size, data volume, and compute produces a foundation model for natural, robust humanoid whole-body control with downstream uses in kinematic planning and vision-language-action models.
-
SSPO: Subsentence-level Policy Optimization
SSPO computes policy importance ratios at the subsentence level with entropy-adjusted clipping bounds, yielding higher average scores than GRPO and GSPO on math reasoning benchmarks with Qwen models.
-
The Realignment Problem: When Right becomes Wrong in LLMs
TRACE is a three-stage optimization framework that realigns LLMs to new policies by categorizing preference conflicts, scoring impact via bi-level optimization, and applying hybrid losses without new human annotations.
-
Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
RLVR on synthetic mazes enables VLMs to solve spatial reasoning tasks unreachable by the base model and generalizes to real-world navigation benchmarks.
-
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
RLBoost harvests preemptible GPUs for RL rollout via a hybrid architecture with adaptive offload, pull-based transfer, and token-level migration, delivering 1.51x-1.97x throughput and 28-49% better cost efficiency than on-demand-only setups.
-
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
ACTG-ARL uses a hierarchical DP feature-learning plus conditional-generation pipeline followed by anchored RL to raise MAUVE scores by 20% and improve instruction following under privacy constraints.
-
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
NashPG is a policy-gradient method with iteratively refined regularization that guarantees monotonic convergence to Nash equilibria in two-player zero-sum extensive-form games and scales to large benchmarks.
-
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
SSL4RL reformulates self-supervised learning objectives into dense, verifiable reward signals for RL-based fine-tuning of vision-language models, yielding performance gains on reasoning benchmarks.
-
Vision-LLMs for Spatiotemporal Traffic Forecasting
ST-Vision-LLM reframes spatiotemporal traffic forecasting as vision-language fusion, using visual encoders on traffic grids and efficient numerical tokenization to achieve 15.6% better long-term accuracy and 30% gains in few-shot cross-domain settings.
-
Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance
DyKnow-RAG uses Group Relative Policy Optimization with dual-group rollouts and posterior-driven advantage scaling to optimize context utilization in RAG for e-commerce relevance, showing offline gains and production lifts when deployed at Taobao.
-
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
-
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
The paper defines a Gradient Gap for RLVR policy gradients and proves a sharp step-size threshold below which training converges and above which it collapses, with predictions for length and success-rate scaling validated in simulations and on Qwen2.5-Math-7B.
-
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
-
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
The paper identifies that importance sampling ratios in outcome-supervised RL misallocate credit by creating unbalanced token updates, and introduces ASPO to correct the asymmetry for positive-advantage tokens.
-
A KL-regularization Framework for Learning to Plan with Adaptive Priors
PO-MPC unifies prior MPPI-based RL approaches under a single KL-regularized framework that uses the planner distribution as a prior, with new variations yielding performance gains in experiments.
-
Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
MINTO sets bootstrapped targets to the minimum of online and target network estimates, yielding faster stable value learning across online/offline RL and discrete/continuous actions.
-
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
Post-training on reasoning tasks sparks the emergence of specialized attention heads that enable structured computation, with SFT adding stable heads while GRPO uses dynamic activation and pruning tied to reward signals, and controllable think models relying on compensatory heads instead of specific
-
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
World-Env replaces physical robot interactions with a world model-based virtual environment and VLM-guided rewards to enable efficient RL post-training for VLA models, showing gains with only five demonstrations per task.
-
Structured In-context Environment Scaling for Large Language Model Reasoning
SIE framework automatically constructs scalable, verifiable reasoning environments from structured data, improving in-domain performance and enabling generalization to out-of-domain math and logic tasks.
-
Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
DRP decouples reasoning from perception in LMMs by using an LLM reasoner to query an LMM observer for visual details as needed, reducing visual grounding loss.
-
Multiplayer Nash Preference Optimization
MNPO extends NLHF to multiplayer Nash games, inheriting equilibrium guarantees while showing empirical gains on instruction-following benchmarks under diverse preferences.
-
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.