Related papers: OAT: Ordered Action Tokenization
Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm,…
Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-domain data, yet…
Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…
Deep reinforcement learning agents often exhibit erratic, high-frequency control behaviors that hinder real-world deployment due to excessive energy consumption and mechanical wear. We systematically investigate action smoothness…
Autoregressive models (ARMs) have become the workhorse for sequence generation tasks, since many problems can be modeled as next-token prediction. While there appears to be a natural ordering for text (i.e., left-to-right), for many data…
Long-horizon planning for robot manipulation is a challenging problem that requires reasoning about the effects of a sequence of actions on a physical 3D scene. While traditional task planning methods are shown to be effective for…
An Optimal Transport (OT)-based decentralized collaborative multi-robot exploration strategy is proposed in this paper. This method is to achieve an efficient exploration with a predefined priority in the given domain. In this context, the…
Despite the success of deep learning-based algorithms, it is widely known that neural networks may fail to be robust. A popular paradigm to enforce robustness is adversarial training (AT), however, this introduces many computational and…
We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up…
Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration…
Autoregressive generative models can estimate complex continuous data distributions, like trajectory rollouts in an RL environment, image intensities, and audio. Most state-of-the-art models discretize continuous data into several bins and…
In recent years, the performance of action recognition has been significantly improved with the help of deep neural networks. Most of the existing action recognition works hold the \textit{closed-set} assumption that all action categories…
A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data, using some data collection policy, and then learn from this data to perform various tasks, using offline…
The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling…
Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by…
Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass marginal prediction. However, many applications…
The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of…
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific…
Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies.…
Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of…