Related papers: Robometer: Scaling General-Purpose Robotic Reward …

Recent advances in video diffusion models shows promise for generating robotic decision-making data, with trajectory conditions further enabling fine-grained control. However, existing methods primarily focus on individual object motion and…

The main challenge in developing effective reinforcement learning (RL) pipelines is often the design and tuning the reward functions. Well-designed shaping reward can lead to significantly faster learning. Naively formulated rewards,…

Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments. However, existing robotic memory benchmarks still lack…

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

This paper presents a novel approach that combines the advantages of both model-based and learning-based frameworks to achieve robust locomotion. The residual modules are integrated with each corresponding part of the model-based framework,…

Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedback. However, large-scale preference datasets, whether collected from crowdsourced…

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and planning for such robotic agents is a generalizable reward…

Learning from Demonstration depends on a robot learner generalising its learned model to unseen conditions, as it is not feasible for a person to provide a demonstration set that accounts for all possible variations in non-trivial tasks.…

In Reward Learning (ReL), we are given feedback on an unknown target reward, and the goal is to use this information to recover it in order to carry out some downstream application, e.g., planning. When the feedback is not informative…

In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and…

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

Accurate and robust trajectory predictions of road users are needed to enable safe automated driving. To do this, machine learning models are often used, which can show erratic behavior when presented with previously unseen inputs. In this…

Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…

Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success…

Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., DreamPRM) aligns…

Large, general-purpose robotic policies trained on diverse demonstration datasets have been shown to be remarkably effective both for controlling a variety of robots in a range of different scenes, and for acquiring broad repertoires of…

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

Data scaling and standardized evaluation benchmarks have driven significant advances in natural language processing and computer vision. However, robotics faces unique challenges in scaling data and establishing evaluation protocols.…

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing…