Related papers: GCImOpt: Learning efficient goal-conditioned polic…

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However,…

In this paper, we consider the problem of learning policies to control a large number of homogeneous robots. To this end, we propose a new algorithm we call Graph Policy Gradients (GPG) that exploits the underlying graph symmetry among the…

Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…

In this work we are the first to present an offline policy gradient method for learning imitative policies for complex urban driving from a large corpus of real-world demonstrations. This is achieved by building a differentiable data-driven…

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function. However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and…

Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is…

We report results obtained and insights gained while answering the following question: how effective is it to use a simulator to establish path following control policies for an autonomous ground robot? While the quality of the simulator…

We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage…

For the application of MPC design in on-line regulation or tracking control problems, several studies have attempted to develop an accurate model, and realize adequate uncertainty description of linear or non-linear plants of the processes.…

In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as…

Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during…

Modern aerospace guidance systems demand rigorous constraint satisfaction, optimal performance, and computational efficiency. Traditional analytical methods struggle to simultaneously satisfy these requirements. While data driven methods…

We propose an architecture for learning complex controllable behaviors by having simple Policies Modulate Trajectory Generators (PMTG), a powerful combination that can provide both memory and prior knowledge to the controller. The result is…

Imitation learning has enabled robots to perform complex, long-horizon tasks in challenging dexterous manipulation settings. As new methods are developed, they must be rigorously evaluated and compared against corresponding baselines…

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…

Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on…

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…

Traditional dynamic models of continuum robots are in general computationally expensive and not suitable for real-time control. Recent approaches using learning-based methods to approximate the dynamic model of continuum robots for control…

Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos,…