Related papers: Speedup Patch: Learning a Plug-and-Play Policy to …
Recent advances in robotic policy learning have enabled complex manipulation in real-world environments, yet the execution speed of these policies often lags behind hardware capabilities due to the cost of collecting faster demonstrations.…
Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data-driven framework to accelerate MPC by replacing online optimization with a nonparametric policy…
Imitation learning has shown great promise in robotic manipulation, but the policy's execution is often unsatisfactorily slow due to commonly tardy demonstrations collected by human operators. In this work, we present DemoSpeedup, a…
Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…
We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…
Failure is inevitable for embodied navigation in complex environments. To enhance the resilience, replanning (RP) is a viable option, where the robot is allowed to fail, but is capable of adjusting plan until success. However, existing RP…
We present two novel optimizations that accelerate clock-based spiking neural network (SNN) simulators. The first one targets spike timing dependent plasticity (STDP). It combines lazy- with event-driven plasticity and efficiently…
Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov…
This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…
Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…
Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases…
While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…
The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL…
Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a novel policy optimization method based on Constrained…
For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as…
Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing…
Massively parallel GPU simulation environments have accelerated reinforcement learning (RL) research by enabling fast data collection for on-policy RL algorithms like Proximal Policy Optimization (PPO). To maximize throughput, it is common…
A queue is required when a service provider is not able to handle jobs arriving over the time. In a highly flexible and dynamic environment, some jobs might demand for faster execution at run-time especially when the resources are limited…
Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…
Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we…