Related papers: Towards Bridging the Gap between Large-Scale Pretr…
Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly…
Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…
Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…
Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and…
Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample…
Massively parallel simulation has reduced reinforcement learning (RL) training time for robots from days to minutes. However, achieving fast and reliable sim-to-real RL for humanoid control remains difficult due to the challenges introduced…
Automated vehicle control using reinforcement learning (RL) has attracted significant attention due to its potential to learn driving policies through environment interaction. However, RL agents often face training challenges in sample…
Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for…
Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning…
The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are…
Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional…
Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…
Recent advances in deep Reinforcement Learning (RL) have created unprecedented opportunities for intelligent automation, where a machine can autonomously learn an optimal policy for performing a given task. However, current deep RL…
Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…
Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even…
Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising approach has not yet enjoyed similarly widespread adoption…