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%).
1910
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.
IRumAI is the first RL agent for Indian Rummy, trained on weak heuristics to beat strong search opponents at 7000x speed.
DeFAb is a large-scale, formally verifiable benchmark for defeasible abduction derived from 18 knowledge bases, demonstrating that frontier LLMs achieve 7.8-65% accuracy versus 100% for a rule-based solver with polynomial-time checks.
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.
citing papers explorer
-
On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse
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.
-
Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
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.
-
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
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.
-
AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning
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.
-
ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning
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 Models)
Weak-to-strong generalization is nearly inevitable in linear logistic regression for most student-teacher pairs without any model capacity mismatch.
-
Structural Equivalence and Learning Dynamics in Delayed MARL
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.
-
Language Game: Talking to Non-Human Systems
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.
-
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
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.
-
Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
-
DecompRL: Solving Harder Problems by Learning Modular Code Generation
DecompRL is an RL method that learns modular code decomposition for LLMs, enabling exponential candidate generation via recombination to solve harder coding problems with lower GPU cost.
-
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
-
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
TRIAGE augments GRPO with role-typed segment rewards derived from a judge that detects regression and exploration, yielding higher success rates and fewer turns on ALFWorld, Search-QA, and WebShop.
-
STEMGym: Benchmarking Sequential Decision-Making under Dose Budgets in Autonomous Electron Microscopy
STEMGym benchmark demonstrates that perception pipelines dominate dose efficiency in autonomous STEM over navigation methods across 33 agent setups.
-
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Proposes Monotonic Inference Policy Improvement (MIPI) objective and MIPU two-step update framework to address objective misalignment between training and inference policies in LLM reinforcement learning.
-
CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning
CRAFT is a three-pillar credit assignment scheme that uses counterfactual token importance from GRPO sibling rollouts to provide signed per-token distillation signals in self-distilled agentic RL.
-
A Markov Chain Approach to Preference Alignment
MCHF defines a Markov kernel from pairwise utilities U and proves geometric convergence to its stationary distribution at a rate set by the seminorm measuring non-transitivity of U, with first-order equivalence to RLHF and NLHF solutions.
-
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
-
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
TAPO constructs learnable micro-reflective trajectories from contrastive model rollouts during RL training to provide explicit error diagnoses and corrections, reporting consistent gains over GRPO on AIME and HMMT math benchmarks.
-
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
PowerOPD applies the Box-Cox power transformation to create natively bounded, sign-consistent rewards for on-policy distillation, delivering up to +6.37 Avg@8 gains over vanilla OPD on math reasoning benchmarks while cutting compute costs.
-
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
SWITCH uses explicit <swi> and </swi> boundary tokens to make latent chain-of-thought compatible with on-policy RL (GRPO) and open to causal mechanistic probing, outperforming prior hidden-state recurrence methods.
-
SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning
SymQNet uses offline RL to amortize acquisition for adaptive Hamiltonian learning, delivering 47-72x lower decision latency than online Bayesian baselines on Ising models while keeping posterior updates.
-
Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
Non-quadratic Mirror Descent exhibits exponential initialization sensitivity in convex settings, shown via 3D constructions and KL-regularized simplex examples, with Bregman anchoring proposed for stabilization.
-
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
Flow-DPPO replaces PPO ratio clipping with an asymmetric KL divergence mask for flow models, claiming higher rewards, reduced forgetting, and stable multi-epoch training.
-
Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models
VLM-Safe-RL adds frozen VLM signals as anticipatory costs to the CMDP Lagrangian update via dual-path CLIP, VLM-Lagrange, and confidence gating, outperforming baselines on Safety-Gymnasium FormulaOne while showing partial generalization.
-
Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation
AR-OPD disentangles privileged supervision via anchored residual guidance to reduce hindsight leakage in on-policy distillation, reporting gains of 2.3 points over full privileged OPD and 7.9 over SFT on reasoning tasks.
-
Escaping the KL Agreement Trap in On-Policy Distillation
KAT detects persistent low-KL agreement traps in on-policy distillation via a dynamic threshold to filter weak supervision, improving avg@k by 2.66% and pass@k by 3.43% on four math benchmarks while shortening rollouts by 59.73%.
-
Reinforcement Learning for Flow-Matching Policies with Density Transport
RLDT fine-tunes pretrained flow-matching policies for continuous control by aligning them to a max-entropy RL transport field constructed via SVGD, using expected-target estimation for stable multi-step updates.
-
Adversarial Robustness of Activation Steering in Large Language Models
First systematic test shows activation steering robustness drops sharply (up to 64%) under adversarial input perturbations across multiple extraction methods, models, and personas.
-
Learn to Match: Two-Sided Matching with Temporally Extended Feedback
Learn2Match is a POMG-based MARL benchmark for two-sided matching with temporally extended feedback; independent PPO yields higher social welfare and lower regret than CA-ETC but higher information-friction loss.
-
Your GFlowNet Secretly Learns an Optimal Transport Plan
Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
-
Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification
Introduces KL misspecification for bandits and RL under function approximation and proves explicit KL-regret bounds for regression-based Gibbs algorithms that recover the realizable case.
-
Reinforcement Learning from Rich Feedback with Distributional DAgger
DistIL applies distributional DAgger with forward cross-entropy to achieve monotonic policy improvement and better Pass@N from rich feedback in RL for reasoning tasks.
-
Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
CVT-RL improves verified task success to 78.9% and reduces hacking to 3.9% in long-horizon language agents by combining intervention-validity gating with a selection-adjusted doubly robust PCCC estimator.
-
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
TTT-RTL performs per-design test-time RL on an LLM policy with EDA-derived PPA rewards and an adaptive KL controller, reducing geometric-mean PPA product by 65.1% on RTLLM v2.0 and ADP by 59.4% on an industrial FPU unit.
-
Drifting Preference Optimization for One-Step Generative Models
DrPO enables online preference optimization for deterministic one-step generators via non-parametric dipole updates from ranked samples plus base-model drift, without reward backpropagation.
-
Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing
SAGC dynamically adjusts group sizes in synchronous GRPO and DAPO via online constrained optimization to cut stragglers, improve wall-clock speed, and maintain or improve rewards and downstream reasoning performance.
-
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
In navigation tasks, DQN learns MDP-homomorphism-invariant representations while PPO learns action-symmetric ones despite comparable performance, with effects on transfer and in LLMs.
-
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
PromptPO shows LLMs can act as black-box policy optimizers for sequential RL when leveraging prior knowledge, matching baselines in exploration and robotics but underperforming in MuJoCo.
-
TriSearch: Learning to Optimize Triangulations via Bistellar Flips
TriSearch is an RL framework that optimizes triangulations of polytopes using bistellar flips with a circuit-supported subtriangulation action representation, generalizing zero-shot to larger instances and outperforming prior samplers in 3D and 4D.
-
RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood
RL2ML introduces a parameterized family of surrogate objectives bridging RL and ML with unbiased gradient estimators, group-level update-scale analysis, and metric-dependent optimization for finite-rollout LLM training.
-
Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
CARL trains a critic for segment-level credit assignment from binary outcomes in LLM tool-use trajectories, yielding 6.7-9.7 point accuracy gains and 53% fewer calls on solvable questions across five benchmarks.
-
Explicit Critic Guidance for Aligning Diffusion Models
Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.
-
BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning
BASIS achieves superior value estimation and policy optimization in LLM reasoning with single rollouts by batchwise information sharing compared to existing single and multi-rollout methods.
-
Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
SILO outperforms five baselines on eight protein fitness landscapes by using trajectory-level imitation on trajectories selected via hierarchical beam search and biological proxy guidance under limited oracle budgets.
-
Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
Wasserstein policy gradient converges globally in entropy-regularized RL via Bellman-induced distributional PL geometry and uniform LSI, yielding geometric contraction up to discretization bias.
-
The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible
No confidence-gated RL policy can achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight when tasks exceed the agent's competence, because non-affine autonomy incentives destroy strict properness of scoring rules and cause confidence inflation.
-
Not only where, But when: Temporal Scheduling for RLVR
Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than static allocation.
-
Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
Recurrent trace units enable exact RTRL with linear time/memory for streaming RL under partial observability, sustaining performance on long-chain memory tasks where TBPTT baselines collapse.
-
Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
DMGG uses reinforcement learning to generate microcanonical graph ensembles with exact assortativity constraints via degree-preserving rewirings, claiming faster generation and better diversity than ERGM approaches.