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%).
1593
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
-
Extreme dynamic symmetry enables omnidirectional and multifunctional robots
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.
-
Certified Gradient-Based Contact-Rich Manipulation via Smoothing-Error Reachable Tubes
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.
-
LeLaR: The First In-Orbit Demonstration of an AI-Based Satellite Attitude Controller
First in-orbit demonstration of a DRL-trained AI satellite attitude controller that performs robust inertial pointing after sim-to-real transfer.
-
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.
-
OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation
OOPSIEVERSE is a new damage-aware simulation benchmark for household robot manipulation that converts contact, thermal, and fluid signals into task-agnostic damage metrics and demonstrates uses in safer policy learning and benchmarking.
-
Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot
Reinforcement learning produces a policy for passive inline skating on a humanoid robot that achieves up to 50% lower cost of transport than walking and transfers zero-shot to physical hardware.
-
DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand
DexCompose achieves 77.4% average success on 16 composite dexterous tasks by using role-aware residual composition with explicit finger ownership to combine pretrained policies without destructive interference.
-
Learning Object Manipulation from Scratch via Contrastive Interaction
IWR improves CRL sample efficiency and performance in interaction-rich manipulation by interaction-aware resampling that preserves mode boundaries, yielding 19.8% average gains and a real-world air-hockey agent.
-
Learning Controlled Separation of Small Objects Between Two Fingers with a Tactile Skin
A tactile-skin-equipped robotic hand learns via RL to perform controlled separation of small pellets between fingers, showing benefits of spatial tactile resolution and successful sim-to-real transfer.
-
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
-
Micro-Swarm Locomotion Optimization in Dynamic Flow using Multi-Objective Multi-Agent Reinforcement Learning
Hybrid CFD-MOMARL framework with PCGrad enables micro-swarm navigation in pulsatile flow, achieving progress 6.5-7.0, energy 0.63-0.65, smoothness 0.97-0.99 with emergent behaviors.
-
AcroRL: Learning Aggressive Quadrotor Inversion using Bidirectional Thrust
Reinforcement learning policies for quadrotor inversion transitions with bidirectional thrust outperform optimization baselines by 32% in position RMSE and 57% in settling time in simulation, with successful hardware validation.
-
roto 2.0: The Robot Tactile Olympiad
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.
-
Learning Robust Dexterous In-Hand Manipulation from Joint Sensors with Proprioceptive Transformer
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.
-
4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving
4DLidarOpen is a new open dataset providing synchronized 4D FMCW Lidar velocity measurements, multi-Lidar and camera data, and 3D bounding-box annotations with track IDs to support benchmarks on 3D detection, BEV segmentation, flow prediction, and motion forecasting.
-
Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization
An adaptive smooth Tchebycheff controller for multi-objective RL lets agents reach non-convex Pareto regions in robotic tasks while avoiding the instability of static non-linear scalarizations.
-
Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.
-
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.
-
HiPAN: Hierarchical Posture-Adaptive Navigation for Quadruped Robots in Unstructured 3D Environments
HiPAN enables quadruped robots to navigate unstructured 3D environments more successfully by combining a high-level posture-adaptive policy with a low-level controller and curriculum learning on depth images.
-
KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning
KinDER is a new open-source benchmark that demonstrates substantial gaps in current robot learning and planning methods for handling physical constraints.
-
HANDFUL: Sequential Grasp-Conditioned Dexterous Manipulation with Resource Awareness
HANDFUL learns resource-aware grasps using finger contact rewards and curriculum learning to improve success on sequential dexterous tasks in simulation and on a real LEAP hand.
-
Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty
MATCH trains hybrid position-force RL policies that achieve up to 10% higher success rates and 5x fewer breaks than pose-only policies in fragile peg-in-hole tasks under localization uncertainty, with strong sim-to-real results.
-
AeroBridge-TTA: Test-Time Adaptive Language-Conditioned Control for UAVs
AeroBridge-TTA achieves +22 pt average gains on out-of-distribution UAV dynamics mismatches by updating a latent state online from observed transitions in a language-conditioned policy.
-
DART: Learning-Enhanced Model Predictive Control for Dual-Arm Non-Prehensile Manipulation
DART is the first claimed framework for non-prehensile dual-arm tray manipulation, integrating MPC with physics-based, online regression, and reinforcement learning dynamics models, validated in simulation.
-
Evolving the Complete Muscle: Efficient Morphology-Control Co-design for Musculoskeletal Locomotion
Spectral Design Evolution co-optimizes complete muscle morphology (strength, velocity, stiffness) and control, achieving better efficiency and stability than fixed-morphology baselines on locomotion tasks.
-
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.
-
Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing
A DRL policy learns racing controls from depth spectral distributions using a non-geometric physics-informed reward, achieving 12% better performance than humans on out-of-distribution tracks with under 1% of baseline computation.
-
Robots that learn to evaluate models of collective behavior
A robotic fish learns goal-directed policies in simulation and interacts with live fish to quantify how well different behavioral models match real responses using Wasserstein distances on performance metrics.
-
When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
DGBA enables reliable backdoor attacks on real-world RL policies under partial observability by learning stochastic visual triggers via conditional diffusion and using advantage-based poisoning at critical states.
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
-
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
-
Freeform Preference Learning for Robotic Manipulation
Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference baselines by 38 percentage points.
-
ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control
ReactiveBFM introduces a real-time closed-loop planning-control system for humanoids using curriculum-based error recovery and asynchronous replanning, achieving 93.1% success under severe perturbations in sim-to-sim tests.
-
AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance
AnyBody distills a privileged teacher tracker into a latent unit-sphere representation and uses a masked transformer to drive humanoid control from arbitrary keypoint subsets.
-
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
-
Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
Crazyflow is a fast, differentiable, GPU-accelerated drone simulator in JAX that enables large-scale parallel simulation and in-flight reinforcement learning for aerial robots.
-
A Sonar-Visual Dataset for Cross-Modal Underwater Robot Perception
Presents the SOVIS sonar-visual dataset of over 76k paired frames from 17 dives, an interactive annotation tool, and a cross-modal fish detection demo showing 7x mAP improvement over camera-only baseline.
-
S2M-Trek: From Single to Multi-Sphere Transport via Per-Frame Deep Sets on a Wheel-Legged Robot
Per-Frame Deep Sets enables scaling single-sphere to five-sphere transport on a quadruped by performing permutation-invariant pooling within each history frame, reaching 100% no-drop success in simulation where standard encoders plateau.
-
Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
Dynamic scene graphs serve as explicit memory to improve imitation learning policies for spatial-temporal reasoning under partial observability in mobile and tabletop manipulation.
-
Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
Trains embodiment-aware value functions on up to 50 robots and applies their gradients as differentiable surrogates to optimize held-out robot designs with over 1100 parameters.
-
Building Generalization Into Behavior Generation Via Adaptive Compositions of Regularities
Adaptive composition of regularities in a differentiable network enables context-appropriate behavior in novel conditions for a simulated robotics problem, succeeding except when regularities are provably insufficient.
-
Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement Learning
Feat2Go uses patch-level similarity from a visual world model and trend-based clustering to create progress targets for training value models that improve reward shaping in embodied RL for VLA policies, yielding large gains on ManiSkill3 and RoboTwin benchmarks.
-
UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms
UniLab is a CPU/GPU heterogeneous system for robot RL training using MuJoCoUni and MotrixSim backends that reports 3-10x end-to-end efficiency improvements and cross-platform compatibility beyond CUDA.
-
S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion
A quadruped robot with a three-degree-of-freedom active spine reaches 6.9 m/s top speed and 7.2 rad/s turning rate via an RL framework that rewards spine engagement and gallop gaits.
-
Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty
A credibility-aware RL framework with CW-VL, CI-VO, and risk-aware COLREGs embedding improves USV collision avoidance and rule compliance in simulations under perceptual uncertainty.
-
Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning
Robust Koopman-CBF SAC learns Koopman predictors from data, tightens lifted CBF constraints with a data-estimated residual margin, and applies a QP safety filter inside SAC, reporting zero constraint violations on CartPole while matching unconstrained returns.
-
When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
Auto-Robotist converts morphology search traces into a transferable skill library that boosts cold-start performance and outperforms GA when transferring to larger 10x10 design spaces across seven EvoGym tasks.
-
ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots
ECo-MoE co-optimizes latent robot genotypes and a gated mixture of control experts to improve evolvability in robot body-controller co-design.
-
Direct Dynamic Retargeting for Humanoid Imitation Learning from Videos
DDR is a single-stage task-space framework using sampling-based MPC in a physics simulator to produce high-fidelity dynamically feasible references from video demos, claimed to outperform geometric and indirect retargeting baselines in tracking accuracy and to speed up RL training for agile humanoid
-
Vision-Based Agile Landing on Turbulent Waters
Reinforcement learning policy trained on synthetic visual features in simulation enables zero-shot real-world agile multirotor landing on turbulent maritime platforms without explicit platform-state estimation.