This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses.

He Xiaopeng launches Xpeng's next-gen Iron humanoid robot during a press conference at the company's headquarters in Guangzhou on November 5, 2025. He Xiaopeng launches Xpeng's next-gen Iron humanoid robot during a press conference at the company's headquarters in Guangzhou on November 5, 2025. It was a controversy laced with pride for He Xiaopeng. In November, He, the founder and CEO of Chinese physical AI firm XPeng, had just debuted his new humanoid robot, IRON, whose balance, posture shifts, and coquettish swagger mirrored human motion with such eerie precision that a slew of netizens accused him of faking the demonstration by putting a human in a bodysuit. To silence the naysayers, He boldly cut open the robot's leg live on stage to reveal the intricate mechanical systems that allow it to adapt to uneven surfaces and maintain stability just like the human body. "At first, it made me sad," He tells TIME in his Guangzhou headquarters.

Former OpenAI employee Daniel Kokotajlo says progress to AGI is'somewhat slower' than first predicted

In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it generalizes effectively. Such \emph{direct sim2real} transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the simulator. In this work, we show that in many regimes, while direct sim2real transfer may fail, we can utilize the simulator to learn a set of \emph{exploratory} policies which enable efficient exploration in the real world. In particular, in the setting of low-rank MDPs, we show that coupling these exploratory policies with simple, practical approaches---least-squares regression oracles and naive randomized exploration---yields a polynomial sample complexity in the real world, an exponential improvement over direct sim2real transfer, or learning without access to a simulator. To the best of our knowledge, this is the first evidence that simulation transfer yields a provable gain in reinforcement learning in settings where direct sim2real transfer fails. We validate our theoretical results on several realistic robotic simulators and a real-world robotic sim2real task, demonstrating that transferring exploratory policies can yield substantial gains in practice as well.

We present BricksRL, a platform designed to democratize access to robotics for reinforcement learning research and education.

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art disentanglement models have heavily relied on synthetic toy data-sets. In this paper, we propose a novel data-set which consists of over 1 million images of physical 3D objects with seven factors of variation, such as object color, shape, size and position. In order to be able to control all the factors of variation precisely, we built an experimental platform where the objects are being moved by a robotic arm. In addition, we provide two more datasets which consist of simulations of the experimental setup. These datasets provide for the first time the possibility to systematically investigate how well different disentanglement methods perform on real data in comparison to simulation, and how simulated data can be leveraged to build better representations of the real world. We provide a first experimental study of these questions and our results indicate that learned models transfer poorly, but that model and hyperparameter selection is an effective means of transferring information to the real world.

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to potentially dangerous behavior. Hence safe exploration is a critical issue in applying RL algorithms in the real world. This problem has been recently well studied under the Constrained Markov Decision Process (CMDP) Framework, where in addition to single-stage rewards, an agent receives single-stage costs or penalties as well depending on the state transitions. The prescribed cost functions are responsible for mapping undesirable behavior at any given time-step to a scalar value.

In visual-input sim-to-real scenarios, to overcome the reality gap between images rendered in simulators and those from the real world, domain adaptation, i.e., learning an aligned representation space between simulators and the real world, then training and deploying policies in the aligned representation, is a promising direction. Previous methods focus on same-modal domain adaptation. However, those methods require building and running simulators that render high-quality images, which can be difficult and costly. In this paper, we consider a more cost-efficient setting of visual-input sim-to-real where only low-dimensional states are simulated. We first point out that the objective of learning mapping functions in previous methods that align the representation spaces is ill-posed, prone to yield an incorrect mapping. When the mapping crosses modalities, previous methods are easier to fail.

Cross-domain transfer in robotic manipulation remains a longstanding challenge due to the significant domain gap between simulated and real-world environments. Existing methods such as domain randomization, adaptation, and sim-real calibration often require extensive tuning or fail to generalize to unseen scenarios. To address this issue, we observe that if domain-invariant features are utilized during policy training in simulation, and the same features can be extracted and provided as the input to policy during real-world deployment, the domain gap can be effectively bridged, leading to significantly improved policy generalization. Accordingly, we propose Semantic 2D Gaussian Splatting (S2GS), a novel representation method that extracts object-centric, domain-invariant spatial features. S2GS constructs multi-view 2D semantic fields and projects them into a unified 3D space via feature-level Gaussian splatting. A semantic filtering mechanism removes irrelevant background content, ensuring clean and consistent inputs for policy learning. To evaluate the effectiveness of S2GS, we adopt Diffusion Policy as the downstream learning algorithm and conduct experiments in the ManiSkill simulation environment, followed by real-world deployment. Results demonstrate that S2GS significantly improves sim-to-real transferability, maintaining high and stable task performance in real-world scenarios.