An official website of the United States government
Robot social navigation is influenced by human preferences and environment-specific scenarios such as elevators and doors, thus necessitating end-user adaptability. State-of-the-art approaches to social navigation fall into two categories: model-based social constraints and learning-based approaches. While effective, these approaches have fundamental limitations – model-based approaches require constraint and parameter tuning to adapt to preferences and new scenarios, while learning-based approaches require reward functions, significant training data, and are hard to adapt to new social scenarios or new domains with limited demonstrations.In this work, we propose Iterative Dimension Informed Program Synthesis (IDIPS) to address these limitations by learning and adapting social navigation in the form of human-readable symbolic programs. IDIPS works by combining pro-gram synthesis, parameter optimization, predicate repair, and iterative human demonstration to learn and adapt model-free action selection policies from orders of magnitude less data than learning-based approaches. We introduce a novel predicate repair technique that can accommodate previously unseen social scenarios or preferences by growing existing policies.We present experimental results showing that IDIPS: 1) synthesizes effective policies that model user preference, 2) can adapt existing policies to changing preferences, 3) can extend policies to handle novel social scenarios such as locked doors, and 4) generates policies that can be transferred from simulation to real-world robots with minimal effort.
more »
« less
This content will become publicly available on March 5, 2026
Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning
Offline safe reinforcement learning (OSRL) aims to learn policies with high rewards while satisfying safety constraints solely from data collected offline. However, the learned policies often struggle to handle states and actions that are not present or out-of-distribution (OOD) from the offline dataset, which can result in violation of the safety constraints or overly conservative behaviors during their online deployment. Moreover, many existing methods are unable to learn policies that can adapt to varying constraint thresholds. To address these challenges, we propose constraint-conditioned actor-critic (CCAC), a novel OSRL method that models the relationship between state-action distributions and safety constraints, and leverages this relationship to regularize critics and policy learning. CCAC learns policies that can effectively handle OOD data and adapt to varying constraint thresholds. Empirical evaluations on the benchmarks show that CCAC significantly outperforms existing methods for learning adaptive, safe, and high-reward policies.
more »
« less
- Award ID(s):
- 2340776
- PAR ID:
- 10582382
- Publisher / Repository:
- The Thirteenth International Conference on Learning Representations
- Date Published:
- Subject(s) / Keyword(s):
- Offline Safe Reinforcement Learning Actor-Critic Out-of-distribution Detection Zero-shot Adaptation
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Optimizing charging protocols is critical for reducing battery charging time and decelerating battery degradation in applications such as electric vehicles. Recently, reinforcement learning (RL) methods have been adopted for such purposes. However, RL‐based methods may not ensure system (safety) constraints, which can cause irreversible damages to batteries and reduce their lifetime. To this end, this article proposes an adaptive and safe RL framework to optimize fast charging strategies while respecting safety constraints with a high probability. In our method, any unsafe action that the RL agent decides will be projected into a safety region by solving a constrained optimization problem. The safety region is constructed using adaptive Gaussian process (GP) models, consisting of static and dynamic GPs, that learn from online experience to adaptively account for any changes in battery dynamics. Simulation results show that our method can charge the batteries rapidly with constraint satisfaction under varying operating conditions.more » « less
-
Safe and Efficient Reinforcement Learning using Disturbance-Observer-Based Control Barrier FunctionsMatni, Nikolai; Morari, Manfred; Pappas, George J. (Ed.)Safe reinforcement learning (RL) with assured satisfaction of hard state constraints during training has recently received a lot of attention. Safety filters, e.g., based on control barrier functions (CBFs), provide a promising way for safe RL via modifying the unsafe actions of an RL agent on the fly. Existing safety filter-based approaches typically involve learning of uncertain dynamics and quantifying the learned model error, which leads to conservative filters before a large amount of data is collected to learn a good model, thereby preventing efficient exploration. This paper presents a method for safe and efficient RL using disturbance observers (DOBs) and control barrier functions (CBFs). Unlike most existing safe RL methods that deal with hard state constraints, our method does not involve model learning, and leverages DOBs to accurately estimate the pointwise value of the uncertainty, which is then incorporated into a robust CBF condition to generate safe actions. The DOB-based CBF can be used as a safety filter with model-free RL algorithms by minimally modifying the actions of an RL agent whenever necessary to ensure safety throughout the learning process. Simulation results on a unicycle and a 2D quadrotor demonstrate that the proposed method outperforms a state-of-the-art safe RL algorithm using CBFs and Gaussian processes-based model learning, in terms of safety violation rate, and sample and computational efficiency.more » « less
-
Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier FunctionsSafe reinforcement learning (RL) with assured satisfaction of hard state constraints during training has recently received a lot of attention. Safety filters, e.g., based on control barrier functions (CBFs), provide a promising way for safe RL via modifying the unsafe actions of an RL agent on the fly. Existing safety filter-based approaches typically involve learning of uncertain dynamics and quantifying the learned model error, which leads to conservative filters before a large amount of data is collected to learn a good model, thereby preventing efficient exploration. This paper presents a method for safe and efficient RL using disturbance observers (DOBs) and control barrier functions (CBFs). Unlike most existing safe RL methods that deal with hard state constraints, our method does not involve model learning, and leverages DOBs to accurately estimate the pointwise value of the uncertainty, which is then incorporated into a robust CBF condition to generate safe actions. The DOB-based CBF can be used as a safety filter with model-free RL algorithms by minimally modifying the actions of an RL agent whenever necessary to ensure safety throughout the learning process. Simulation results on a unicycle and a 2D quadrotor demonstrate that the proposed method outperforms a state-of-the-art safe RL algorithm using CBFs and Gaussian processes-based model learning, in terms of safety violation rate, and sample and computational efficiency.more » « less
-
We extend the learning from demonstration paradigm by providing a method for learning unknown constraints shared across tasks, using demonstrations of the tasks, their cost functions, and knowledge of the system dynamics and control constraints. Given safe demonstrations, our method uses hit-and-run sampling to obtain lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a consistent representation of the unsafe set via solving an integer program. Our method generalizes across system dynamics and learns a guaranteed subset of the constraint. In addition, by leveraging a known parameterization of the constraint, we modify our method to learn parametric constraints in high dimensions. We also provide theoretical analysis on what subset of the constraint and safe set can be learnable from safe demonstrations. We demonstrate our method on linear and nonlinear system dynamics, show that it can be modified to work with suboptimal demonstrations, and that it can also be used to learn constraints in a feature space.more » « less
