LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
hub Canonical reference
Rl-100: Performant robotic manipulation with real-world reinforcement learning
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
SARM2 presents RM, a multi-task stage-aware reward model achieving 80% lower value-estimation MSE, which when used in SPIRAL boosts manipulation task success from ~50% to near-perfect on several benchmarks.
TORL-VLA couples a tactile wrench-aware VLA policy with a lightweight online RL module and an intervention-censored critic to improve success and efficiency on contact-rich robotic tasks.
PACT calibrates credit assignment in HIL-RL by penalizing Bellman targets on suboptimal segments using counterfactual advantages from human-policy preference pairs, yielding 24.5% higher success rates and 1.3x faster convergence on five real-robot tasks.
ZPRL adapts frozen flow-matching imitation policies via RL perturbations on a task-relevant bottleneck latent, yielding 33.7% higher average success on four real-world manipulation tasks than action-residual baselines.
TMRL bridges behavioral cloning pretraining and RL finetuning via diffusion noise and timestep modulation to enable controlled exploration, improving sample efficiency and enabling real-world robot training in under one hour.
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
RL Token enables sample-efficient online RL fine-tuning of large VLAs, delivering up to 3x speed gains and higher success rates on real-robot manipulation tasks within minutes to hours.
A learning-augmented robotic system automated deformable cable insertion and soldering on a live electric-motor production line for 5 hours 10 minutes, producing 108 motors at 99.4% pass rate with under 20 minutes of real-world data per task and no physical fencing.
MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.
SimDist pretrains world models in simulation and adapts them to real-world robots by updating only the latent dynamics model, enabling rapid improvement on contact-rich tasks where prior methods fail.
A unified parameter space and canonical URDF enable cross-embodiment dexterous grasping policies with 81.9% zero-shot success on unseen hands like the 3-finger LEAP Hand.
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.
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.
SyVLA uses Intention Decoupling and similar-sample guided RL on diversified experiences to improve VLA model task success and out-of-distribution generalization while keeping vision-language abilities.
HandelBot refines simulation policies via physical rollouts and residual RL to achieve precise bimanual piano playing, outperforming direct sim transfer by 1.8x with only 30 minutes of real data across five songs.
EXPO-FT enables pretrained VLA policies to reach 30/30 success on complex manipulation tasks using an average of 19.1 minutes of online robot data while outperforming prior RL approaches.
citing papers explorer
-
TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
TMRL bridges behavioral cloning pretraining and RL finetuning via diffusion noise and timestep modulation to enable controlled exploration, improving sample efficiency and enabling real-world robot training in under one hour.
-
Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
-
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
RL Token enables sample-efficient online RL fine-tuning of large VLAs, delivering up to 3x speed gains and higher success rates on real-robot manipulation tasks within minutes to hours.
-
MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks
MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.
-
$\pi^{*}_{0.6}$: 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.