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%).
1295
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 152
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
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.
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
EDGE-OPD adds guided rollouts and evidence masking to on-policy self-distillation, enabling successful learning of target identities where standard OPSD and RLSD fail.
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.
roto 2.0 provides a standardized benchmark for end-to-end blind tactile RL on 16-24 DOF robots, with open-sourced baselines achieving 13 Baoding ball rotations in 10 seconds.
A transformer policy distilled from a privileged RL teacher enables 3.1x faster real-world cube rotation on the ORCA hand using solely joint sensor data by extracting implicit object state from temporal joint patterns.
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
citing papers explorer
-
OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
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.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
On the Importance of Multistability for Horizon Generalization in Reinforcement Learning
Multistability is necessary for temporal horizon generalization in POMDPs, sufficient in simple tasks along with transient dynamics in complex ones, while monostable parallelizable RNNs like SSMs and gated linear RNNs fail by construction.
-
Delightful Gradients Accelerate Corner Escape
Delightful Policy Gradient removes exponential corner trapping in softmax policy optimization for bandits and tabular MDPs, achieving logarithmic escape times and global O(1/t) convergence.
-
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
CuSearch reallocates rollout budget in RLVR toward deeper-search trajectories as a proxy for retrieval supervision density, yielding up to 11.8 exact-match gains over uniform GRPO sampling on ZeroSearch.
-
Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
GCPO uses team-level credit assignment via determinant volume over reward-weighted semantic embeddings to promote non-redundant correct reasoning paths, improving both accuracy and diversity in LLM training.
-
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
Equivariant RL agent synthesizes near-optimal Clifford circuits up to 30 qubits with lower two-qubit gate counts than Qiskit baselines.
-
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
AHD Agent trains a 4B-parameter LLM via agentic RL to actively use tools for automatic heuristic design, matching or exceeding larger baselines across eight domains with fewer evaluations.
-
The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits
The cancellation hypothesis shows how rollout-level rewards produce token-level credit assignment in critic-free RL through cancellation of opposing signals on shared tokens, with empirical support and batching interventions that enhance performance.
-
The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
Anchored Bipolicy Self-Play trains role-specific LoRA adapters on a frozen base model to break self-consistency collapse in self-play red-teaming, yielding up to 100x parameter efficiency and stronger safety on Qwen2.5 models.
-
Your Loss is My Gain: Low Stake Attacks on Liquid Staking Pools
A low-stake adversary can degrade a liquid staking pool's performance via consensus manipulation and profit from the resulting drop in its LST value through application-layer financial positions.
-
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
-
EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training
EVPO adaptively switches between critic-based and batch-mean advantage estimation using batch-level explained variance to provably achieve no greater variance than the better of PPO or GRPO at every step.
-
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Freshness-Aware PER augments prioritized experience replay with exponential age decay based on effective sample size to enable successful reuse of trajectories in LLM and VLM reinforcement learning, outperforming on-policy baselines on agentic tasks.
-
SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
SAT trains multi-LLM teams with sequential block updates to deliver monotonic gains and plug-and-play model swaps that provably improve performance bounds.
-
ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on locomotion and manipulation benchmarks.
-
Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks
PE-MAMoE combines sparsely gated mixture-of-experts actors with a non-parametric phase controller in MAPPO to maintain plasticity under dynamic user mobility and traffic, yielding 26.3% higher normalized IQM return in simulations.
-
Self-Distilled RLVR
RLSD mixes self-distillation for token-level policy difference magnitudes with RLVR for reliable update directions from response correctness to reach higher convergence and better training stability.
-
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
DiffusionNFT performs online RL for diffusion models on the forward process via flow matching and positive-negative contrasts, delivering up to 25x efficiency gains and rapid benchmark improvements over prior reverse-process methods.
-
Mastering Diverse Domains through World Models
DreamerV3 uses world models and robustness techniques to solve over 150 tasks across domains with a single configuration, including Minecraft diamond collection from scratch.
-
Dota 2 with Large Scale Deep Reinforcement Learning
OpenAI Five achieved superhuman performance in Dota 2 by defeating the world champions using scaled self-play reinforcement learning.
-
Solving Rubik's Cube with a Robot Hand
Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.
-
Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
A new RL objective adapts trust-region and off-policy handling automatically via normalized effective sample size of batch policy ratios, matching tuned baselines without new hyperparameters.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
Delay-Empowered Causal Hierarchical Reinforcement Learning
DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.
-
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
-
Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration
QOED selects identifiable parameter directions via Fisher matrix eigenspace analysis and modifies exploration objectives to approximate ideal information gain under bounded nuisance assumptions, yielding 21-35% performance gains in robotic tasks.
-
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Missing old logits in async agentic RL entangle discrepancy and staleness terms in PPO off-policy correction; exact acquisition methods and revised PPO-EWMA restore decoupled updates with reported gains in speed and performance.
-
Holder Policy Optimisation
HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
-
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
-
Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
TAP couples a learner-conditioned policy with diffusion inpainting to generate and selectively inject high-utility tabular augmentations, yielding up to 15.6 pp accuracy gains and 32% RMSE reduction on seven datasets under severe scarcity.
-
Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion
Explicit conditioning of a PPO policy on interpretable stair parameters (height, depth, yaw) yields improved generalization to unseen stairs and reliable real-world traversal on the Unitree G1, including 33 consecutive outdoor steps.
-
Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching
DRIS improves zero-shot sim-to-real transfer for reactive catching by maintaining and acting on sets of randomized dynamics instances instead of single instances per episode.
-
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
VPG-EA applies variational posterior guidance and efficiency-aware distillation to compress LLM reasoning chains while preserving performance.
-
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning
PiCA uses pivot-based potential rewards derived from historical sub-queries to supply trajectory-aware step guidance in agentic RL, delivering 15% gains on QA benchmarks for 3B/7B models.
-
Reinforcing Multimodal Reasoning Against Visual Degradation
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
-
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
MARS replaces additive clipping and soft penalties in multi-agent trust-region methods with a symmetric geometric barrier, matching or exceeding MAPPO and MASPO performance across 47 tasks in eight environments.
-
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
-
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.
-
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
-
$\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin
ξ-DPO rewrites the preference objective as minimizing distance to optimal margins and defines reward as a chosen-to-rejected ratio, yielding a bounded, interpretable margin ξ set directly from the initial reward-gap distribution.
-
Rotation-Preserving Supervised Fine-Tuning
RPSFT improves the in-domain versus out-of-domain performance trade-off during LLM supervised fine-tuning by penalizing rotations in pretrained singular subspaces as a proxy for loss-sensitive directions.
-
AIPO: Learning to Reason from Active Interaction
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
-
SOD: Step-wise On-policy Distillation for Small Language Model Agents
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Listwise Policy Optimization explicitly performs target-projection on the LLM response simplex, unifying and improving group-based RLVR methods with monotonic improvement and flexible divergences.
-
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
DeScore decouples CoT reasoning from reward scoring in video reward models using a two-stage training process to improve generalization and avoid optimization bottlenecks of coupled generative RMs.
-
LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts
LineRides enables commandable bicycle robot stunts via line-guided RL that uses spatial guidelines, a tracking margin for feasibility, distance-based progress, and sparse key-orientations.
-
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
RLearner-LLM achieves up to 6x gains in NLI entailment over standard fine-tuning by using an automated hybrid DPO pipeline that balances logic and fluency across multiple model sizes and domains.
-
SigLoMa: Learning Open-World Quadrupedal Loco-Manipulation from Ego-Centric Vision
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active sampling curriculum, matching expert human teleoperation performance.