Reinforcement Learning in Robotics

Neueste Paper

• CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization

  Elisa Alboni, Gianluigi Grandesso, Gastone Pietro Rosati Papini, Justin Carpentier, Andrea Del Prete · 30. März 2026

  Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful and complementary tools to solve optimal control problems. On the one hand, TO can efficiently compute locally-optimal solutions, but it tends to get stuck in local minima if the problem is not convex. On the other hand, RL is…

• Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models

  Ron Vainshtein, Zohar Rimon, Shie Mannor, Chen Tessler · 30. März 2026

  Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs often require meticulous prompt engineering for specific tasks,…

• Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning

  Jiajun Hu, Nuria Armengol Urpi, Jin Cheng, Stelian Coros · 27. März 2026

  Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time. Naturally, the quality of the pretraining dataset determines the performance of the recovered policies across tas…

• SEVerA: Verified Synthesis of Self-Evolving Agents

  Debangshu Banerjee, Changming Xu, Gagandeep Singh · 27. März 2026

  Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs, which are then tuned per task to improve performance. Howeve…

• Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance

  Dimitris Michailidis, Willem R\"opke, Diederik M. Roijers, Sennay Ghebreab, Fernando P. Santos · 27. März 2026

  Multi-Objective Reinforcement Learning (MORL) aims to learn a set of policies that optimize trade-offs between multiple, often conflicting objectives. MORL is computationally more complex than single-objective RL, particularly as the number of objectives increases. Additionally, when objectives invo…

• Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem

  Hironori Ohigashi, Shinichiro Hamada · 27. März 2026

  Combinatorial optimization problems like the Traveling Salesman Problem are critical in industry yet NP-hard. Neural Combinatorial Optimization has shown promise, but its reliance on online reinforcement learning (RL) hampers deployment and underutilizes decades of algorithmic knowledge. We address …

• C-STEP: Continuous Space-Time Empowerment for Physics-informed Safe Reinforcement Learning of Mobile Agents

  Guihlerme Daubt, Adrian Redder · 26. März 2026

  Safe navigation in complex environments remains a central challenge for reinforcement learning (RL) in robotics. This paper introduces Continuous Space-Time Empowerment for Physics-informed (C-STEP) safe RL, a novel measure of agent-centric safety tailored to deterministic, continuous domains. This …

• OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

  Woo-Jin Ahn, Sang-Ryul Baek, Yong-Jun Lee, Hyun-Duck Choi, Myo-Taeg Lim · 26. März 2026

  Reinforcement learning algorithms typically utilize an interactive simulator (i.e., environment) with a predefined reward function for policy training. Developing such simulators and manually defining reward functions, however, is often time-consuming and labor-intensive. To address this, we propose…

• Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

  Xiang Li, Yuheng Zhang, Nan Jiang · 26. März 2026

  We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a good policy from offline data via pessimism, existing algorithms that are computat…

• Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration

  Guopeng Li, Matthijs T. J. Spaan, Julian F. P. Kooij · 26. März 2026

  When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although offering high sample efficiency, suffer from constraint violati…

• Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning

  Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov, Dmitry Yudin, Aleksandr Panov · 26. März 2026

  This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The method augments egocentric vision with an online 3D scene g…

• A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning

  Sihan Zeng, Sujay Bhatt, Sumitra Ganesh, Alec Koppel · 26. März 2026

  We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optimization in a Markov decision process (MDP). The upper-level decision variable parameterizes the reward of the lower-level MDP, and the upper-level objec…

• Self Paced Gaussian Contextual Reinforcement Learning

  Mohsen Sahraei Ardakani, Rui Song · 26. März 2026

  Curriculum learning improves reinforcement learning (RL) efficiency by sequencing tasks from simple to complex. However, many self-paced curriculum methods rely on computationally expensive inner-loop optimizations, limiting their scalability in high-dimensional context spaces. In this paper, we pro…

• Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

  Dogan Urgun, Gokhan Gungor · 26. März 2026

  Designing effective auxiliary rewards for cooperative multi-agent systems remains a precarious task; misaligned incentives risk inducing suboptimal coordination, especially where sparse task feedback fails to provide sufficient grounding. This study introduces an automated reward design framework th…

• Dual-Gated Epistemic Time-Dilation: Autonomous Compute Modulation in Asynchronous MARL

  Igor Jankowski · 26. März 2026

  While Multi-Agent Reinforcement Learning (MARL) algorithms achieve unprecedented successes across complex continuous domains, their standard deployment strictly adheres to a synchronous operational paradigm. Under this paradigm, agents are universally forced to execute deep neural network inferences…

• End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions

  Zakaria Mhammedi, Alexander Rakhlin, Nneka Okolo · 25. März 2026

  We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains linear. While statistically tractable, prior computationall…

• GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL

  Haoyu Wang, Jingcheng Wang, Shunyu Wu, Xinwei Xiao · 25. März 2026

  Offline reinforcement learning (RL) can fit strong value functions from fixed datasets, yet reliable deployment still hinges on the action selection interface used to query them. When the dataset induces a branched or multimodal action landscape, unimodal policy extraction can blur competing hypothe…

• Learning The Minimum Action Distance

  Lorenzo Steccanella, Joshua B. Evans, \"Ozg\"ur \c{S}im\c{s}ek, Anders Jonsson · 25. März 2026

  This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number o…

• Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning

  Rohan Deb, Stephen J. Wright, Arindam Banerjee · 25. März 2026

  Offline Reinforcement Learning (RL) aims to learn optimal policies from fixed offline datasets, without further interactions with the environment. Such methods train an offline policy (or value function), and apply it at inference time without further refinement. We introduce an inference time adapt…

• Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning

  Chao Han, Stefanos Ioannou, Luca Manneschi, T. J. Hayward, Michael Mangan, Aditya Gilra, Eleni Vasilaki · 25. März 2026

  We investigate neural ordinary and stochastic differential equations (neural ODEs and SDEs) to model stochastic dynamics in fully and partially observed environments within a model-based reinforcement learning (RL) framework. Through a sequence of simulations, we show that neural SDEs more effective…

• Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure

  Davide Di Gioia · 25. März 2026

  Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience, replacing ad hoc biologically inspired timers with a principl…

• A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling

  Ruisong Zhou, Haijun Zou, Li Zhou, Chumin Sun, Zaiwen Wen · 25. März 2026

  Efficient scheduling of directed acyclic graphs (DAGs) in heterogeneous environments is challenging due to resource capacities and dependencies. In practice, the need for adaptability across environments with varying resource pools and task types, alongside rapid schedule generation, complicates the…

• Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman Constraints

  Tian Xu, Chenyang Wang, Xiaochen Zhai, Ziniu Li, Yi-Chen Li, Yang Yu · 25. März 2026

  Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors in behavioral cloning (BC), but often exhibits training instability due to adversarial optimization. To avoid this issue, a class of non-adversarial Q-based imitation learning (IL) methods, represen…

• Multi-Step First: A Lightweight Deep Reinforcement Learning Strategy for Robust Continuous Control with Partial Observability

  Lingheng Meng, Rob Gorbet, Michael Burke, Dana Kuli\'c · 24. März 2026

  Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially capture the underlying state, the problem becomes a Partially Ob…

• PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

  Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang, Ritu Gala, Charles Wang, Sugam Dipak Devare, Khushi Bhardwaj, Abhibha Gupta, Oleksii Kuchaiev, Jiantao Jiao, Jian Zhang, Venkat Srinivasan · 24. März 2026

  Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities,…