As artificial intelligence shifts from pure tool for delegation toward agentic collaboration, its use in the arts can shift beyond the exploration of machine autonomy toward synergistic co-creation. While our earlier robotic works utilized automation to distance the artist's intent from the final mark, we present Companion: an artistic apparatus that integrates a drawing robot with Large Language Models (LLMs) to re-center human-machine presence. By leveraging in-context learning and real-time tool use, the system engages in bidirectional interaction via speech and sketching. This approach transforms the robot from a passive executor into a playful co-creative partner capable of driving shared visual storytelling into unexpected aesthetic territories. To validate this collaborative shift, we employed the Consensual Assessment Technique (CAT) with a panel of seven art-world experts. Results confirm that the system produces works with a distinct aesthetic identity and professional exhibition merit, demonstrating the potential of AI as a highly capable artistic collaborator.

We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training runs on three distinct robotic platforms, we systematically ablate algorithmic, systems, and experimental decisions that are typically left implicit in prior work. We find that some widely used defaults can be harmful, while a set of robust, readily adopted design choices within standard RL practice yield stable learning across tasks and hardware. These results provide the first large-sample empirical study of such design choices, enabling practitioners to deploy online RL with lower engineering effort.

The success of Large Language Models (LLMs) has sparked interest in various agentic applications. A key hypothesis is that LLMs, leveraging common sense and Chain-of-Thought (CoT) reasoning, can effectively explore and efficiently solve complex domains. However, LLM agents have been found to suffer from sub-optimal exploration and the knowing-doing gap, the inability to effectively act on knowledge present in the model. In this work, we systematically study why LLMs perform sub-optimally in decision-making scenarios. In particular, we closely examine three prevalent failure modes: greediness, frequency bias, and the knowing-doing gap. We propose mitigation of these shortcomings by fine-tuning via Reinforcement Learning (RL) on self-generated CoT rationales. Our experiments across multi-armed bandits, contextual bandits, and Tic-tac-toe, demonstrate that RL fine-tuning enhances the decision-making abilities of LLMs by increasing exploration and narrowing the knowing-doing gap. Finally, we study both classic exploration mechanisms, such as $\epsilon$-greedy, and LLM-specific approaches, such as self-correction and self-consistency, to enable more effective fine-tuning of LLMs for decision-making.

How to efficiently finetune robot policies to learn new tasks on the fly? State of the art robotic manipulation policies are based on behaviour cloning of large vision-language-action (VLA) models with billions of parameters on huge teleoperation datasets. While this simple approach has enabled significant advances for robotic manipulation, finetuning of VLA policies for learning new tasks still remains an open problem. In particular, collecting teleoperation datasets requires hundreds of hours of expensive human labour and the alternative, reinforcement learning (RL), can be notoriously sample-inefficient especially for long-horizon tasks. In addition, RL with VLAs imposes several challenges due to the model's size and architectural design. In this work, we propose EXIMO, an efficient algorithm for finetuning of VLA policies. EXIMO operates in three stages: explore, imitate, and optimize. During the explore phase, EXIMO equips the VLA with a vision language model (VLM) that acts as a planner. The VLM thinks and breaks down challenging long-horizon problems into shorter ones for the VLA. The VLM, together with the VLA, is used to collect an orchestrated dataset on new tasks. During the imitate phase, the VLA is finetuned with the orchestrated data. Finally, during the optimize stage, we use residual off-policy RL to further finetune the policy. In our experiments, we ablate all three stages of EXIMO and show that it outperforms existing approaches significantly in terms of sample-efficiency and final performance.

This article provides an introduction to the mathematical foundations and algorithmic frameworks used to align large language models (LLMs) with human intentions, preferences, and values. We discuss standard alignment techniques, such as supervised fine-tuning (SFT), reinforcement learning with human feedback (RLHF), and direct preference optimization (DPO). We also explore the theoretical underpinnings of learning from human preferences, drawing connections to inverse reinforcement learning (IRL), and discrete choice models. We present state-of-the-art algorithms in a tutorial style, discuss their advantages and limitations, and offer insights into practical implementation. Our exposition is intended to serve as a comprehensive resource for researchers and practitioners, providing both a foundational understanding of alignment methodologies and a framework for developing more robust and scalable alignment techniques.

Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50

Learning based methods for dexterous manipulation have made notable progress in recent years, and they can now produce solutions to complex tasks. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that can be observed across many settings is that policies idle, i.e. they cease to move beyond a small region of states, often indefinitely, when they reach certain states. This policy idling is often a reflection of the training data. For instance, it can occur when the data contains small actions in areas where the robot needs to perform high-precision motions, e.g., when preparing to grasp an object or object insertion. Prior works have tried to mitigate this phenomenon e.g. by filtering the training data or modifying the control frequency. However, these approaches can negatively impact policy performance in other ways. As an alternative, we investigate how to leverage the detectability of idling behavior to inform exploration and policy improvement. Our approach, Pause-Induced Perturbations (PIP), applies perturbations at detected idling states, thus helping it to escape problematic basins of attraction. On a range of challenging simulated dual-arm tasks, we find that this simple approach can already noticeably improve test-time performance, with no additional supervision or training. Furthermore, since the robot tends to idle at critical points in a movement, we also find that learning from the resulting episodes leads to better iterative policy improvement compared to prior approaches. Our perturbation strategy also leads to a 15-35% improvement in absolute success rate on a real-world insertion task that requires complex multi-finger manipulation.

Imitation Learning from Observation (IfO) offers a powerful way to learn behaviors at large-scale: Unlike behavior cloning or offline reinforcement learning, IfO can leverage action-free demonstrations and thus circumvents the need for costly action-labeled demonstrations or reward functions. However, current IfO research focuses on idealized scenarios with mostly bimodal-quality data distributions, restricting the meaningfulness of the results. In contrast, this paper investigates more nuanced distributions and introduces a method to learn from such data, moving closer to a paradigm in which imitation learning can be performed iteratively via self-improvement. Our method adapts RL-based imitation learning to action-free demonstrations, using a value function to transfer information between expert and non-expert data. Through comprehensive evaluation, we delineate the relation between different data distributions and the applicability of algorithms and highlight the limitations of established methods. Our findings provide valuable insights for developing more robust and practical IfO techniques on a path to scalable behaviour learning.

Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called "cognitive models" provide formal accounts of such trade-offs in humans, by modeling the weighting of a speaker's competing utility functions in choosing an action or utterance. Here, we show that a leading cognitive model of polite speech can be used to systematically evaluate alignment-relevant trade-offs in language models via two encompassing settings: degrees of reasoning "effort" and system prompt manipulations in closed-source frontier models, and RL post-training dynamics of open-source models. Our results show that LLMs' behavioral profiles under the cognitive model a) shift predictably when they are prompted to prioritize certain goals, b) are amplified by a small reasoning budget, and c) can be used to diagnose other social behaviors such as sycophancy. Our findings from LLMs' post-training dynamics reveal large shifts in values early on in training and persistent effects of the choice of base model and pretraining data, compared to feedback dataset or alignment method. Our framework offers a flexible tool for probing behavioral profiles across diverse model types and gaining insights for shaping training regimes that better control trade-offs between values during model development.

General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks.

High-frequency control in continuous action and state spaces is essential for practical applications in the physical world. Directly applying end-to-end reinforcement learning to high-frequency control tasks struggles with assigning credit to actions across long temporal horizons, compounded by the difficulty of efficient exploration. The alternative, learning low-frequency policies that guide higher-frequency controllers (e.g., proportional-derivative (PD) controllers), can result in a limited total expressiveness of the combined control system, hindering overall performance. We introduce , a novel bi-level policy learning framework for learning both a slow high-level policy (using PPO) and a fast low-level policy (using Evolution Strategies) for solving continuous control tasks. Learning with Evolution Strategies for the lower-policy allows robust learning for long horizons that crucially arise when operating at higher frequencies. This enables to learn to control interactions at a high frequency, benefitting from more efficient exploration and credit assignment than direct high-frequency torque control without the need to hand-tune PD parameters. We empirically demonstrate that can achieve a higher evaluation reward for continuous-control tasks compared to existing approaches, specifically excelling in tasks where high-frequency control is needed, such as those requiring safety-critical fast reactions.

Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues such as NeurIPS, ICML, and ICLR is outpacing the finite capacity of qualified reviewers, leading to concerns about review quality, consistency, and reviewer fatigue. This position paper argues that AI-assisted peer review must become an urgent research and infrastructure priority. We advocate for a comprehensive AI-augmented ecosystem, leveraging Large Language Models (LLMs) not as replacements for human judgment, but as sophisticated collaborators for authors, reviewers, and Area Chairs (ACs). We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making. Crucially, we contend that the development of such systems hinges on access to more granular, structured, and ethically-sourced peer review process data. We outline a research agenda, including illustrative experiments, to develop and validate these AI assistants, and discuss significant technical and ethical challenges. We call upon the ML community to proactively build this AI-assisted future, ensuring the continued integrity and scalability of scientific validation, while maintaining high standards of peer review.

Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL). We present an effective yet simple framework to extend the use of replays across multiple experiments, minimally adapting the RL workflow for sizeable improvements in controller performance and research iteration times. At its core, Replay Across Experiments (RaE) involves reusing experience from previous experiments to improve exploration and bootstrap learning while reducing required changes to a minimum in comparison to prior work. We empirically show benefits across a number of RL algorithms and challenging control domains spanning both locomotion and manipulation, including hard exploration tasks from egocentric vision. Through comprehensive ablations, we demonstrate robustness to the quality and amount of data available and various hyperparameter choices. Finally, we discuss how our approach can be applied more broadly across research life cycles and can increase resilience by reloading data across random seeds or hyperparameter variations.

We investigated whether deep reinforcement learning (deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies. We used deep RL to train a humanoid robot to play a simplified one-versus-one soccer game. The resulting agent exhibits robust and dynamic movement skills, such as rapid fall recovery, walking, turning, and kicking, and it transitions between them in a smooth and efficient manner. It also learned to anticipate ball movements and block opponent shots. The agent’s tactical behavior adapts to specific game contexts in a way that would be impractical to manually design. Our agent was trained in simulation and transferred to real robots zero-shot. A combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training enabled good-quality transfer. In experiments, the agent walked 181% faster, turned 302% faster, took 63% less time to get up, and kicked a ball 34% faster than a scripted baseline.

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulation combines rigid-body physics with learned, realistic rendering via multiple Neural Radiance Fields (NeRFs). We combine teacher-based multi-agent RL and cross-experiment data reuse to enable the discovery of sophisticated soccer strategies. We analyze active-perception behaviors including object tracking and ball seeking that emerge when simply optimizing perception-agnostic soccer play. The agents display equivalent levels of performance and agility as policies with access to privileged, ground-truth state(3). To our knowledge, this paper constitutes a first demonstration of end-to-end training for multi-agent robot soccer, mapping raw pixel observations to joint-level actions, that can be deployed in the real world.

Recent advances in real-world applications of reinforcement learning (RL) have relied on the ability to accurately simulate systems at scale. However, domains such as fluid dynamical systems exhibit complex dynamic phenomena that are hard to simulate at high integration rates, limiting the direct application of modern deep RL algorithms to often expensive or safety critical hardware. In this work, we introduce "Box o Flows", a novel benchtop experimental control system for systematically evaluating RL algorithms in dynamic real-world scenarios. We describe the key components of the Box o Flows, and through a series of experiments demonstrate how state-of-the-art model-free RL algorithms can synthesize a variety of complex behaviors via simple reward specifications. Furthermore, we explore the role of offline RL in data-efficient hypothesis testing by reusing past experiences. We believe that the insights gained from this preliminary study and the availability of systems like the Box o Flows support the way forward for developing systematic RL algorithms that can be generally applied to complex, dynamical systems. Supplementary material and videos of experiments are available at https://sites.google.com/view/box-o-flows/home.

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token prediction led to its role as predominant paradigm. However, the broader field of imitation learning can more effectively utilize the sequential structure underlying autoregressive generation. We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models. We provide a new angle, reformulating inverse soft-Q-learning as a temporal difference regularized extension of MLE. This creates a principled connection between MLE and IRL and allows trading off added complexity with increased performance and diversity of generations in the supervised fine-tuning (SFT) setting. We find clear advantages for IRL-based imitation, in particular for retaining diversity while maximizing task performance, rendering IRL a strong alternative on fixed SFT datasets even without online data generation. Our analysis of IRL-extracted reward functions further indicates benefits for more robust reward functions via tighter integration of supervised and preference-based LLM post-training.

Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly efficient through re-using previously collected sub-optimal data. In this paper we demonstrate how the increased understanding of off-policy learning methods and their embedding in an iterative online/offline scheme (``collect and infer'') can drastically improve data-efficiency by using all the collected experience, which empowers learning from real robot experience only. Moreover, the resulting policy improves significantly over the state of the art on a recently proposed real robot manipulation benchmark. Our approach learns end-to-end, directly from pixels, and does not rely on additional human domain knowledge such as a simulator or demonstrations.

Inverse reinforcement learning (IRL) offers a powerful and general framework for learning humans' latent preferences in route recommendation, yet no approach has successfully addressed planetary-scale problems with hundreds of millions of states and demonstration trajectories. In this paper, we introduce scaling techniques based on graph compression, spatial parallelization, and improved initialization conditions inspired by a connection to eigenvector algorithms. We revisit classic IRL methods in the routing context, and make the key observation that there exists a trade-off between the use of cheap, deterministic planners and expensive yet robust stochastic policies. This insight is leveraged in Receding Horizon Inverse Planning (RHIP), a new generalization of classic IRL algorithms that provides fine-grained control over performance trade-offs via its planning horizon. Our contributions culminate in a policy that achieves a 16-24% improvement in route quality at a global scale, and to the best of our knowledge, represents the largest published study of IRL algorithms in a real-world setting to date. We conclude by conducting an ablation study of key components, presenting negative results from alternative eigenvalue solvers, and identifying opportunities to further improve scalability via IRL-specific batching strategies.

Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration characteristics while final performance does not visibly suffer in the absence of action penalization in line with optimal control theory. In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency, but action costs can be detrimental to exploration during early training. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution, taking advantage of recent results in decoupled Q-learning to scale our approach to high-dimensional action spaces up to dim(A) = 38. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.