Related papers: R2-Dreamer: Redundancy-Reduced World Models withou…

Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the performance such as sample efficiency, asymptotic…

To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies…

Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…

Mask-based lensless imagers are smaller and lighter than traditional lensed cameras. In these imagers, the sensor does not directly record an image of the scene; rather, a computational algorithm reconstructs it. Typically, mask-based…

Model-based reinforcement learning (MBRL) techniques have recently yielded promising results for real-world autonomous racing using high-dimensional observations. MBRL agents, such as Dreamer, solve long-horizon tasks by building a world…

Deep Reinforcement Learning (DRL) experiments are commonly performed in simulated environments due to the tremendous training sample demands from deep neural networks. In contrast, model-based Bayesian Learning allows a robot to learn good…

Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed automatically and efficiently from raw sensory inputs (such as…

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations,…

Deepfake generators evolve quickly, making exhaustive data collection and repeated retraining impractical. We argue that model merging is a natural fit for deepfake detection: unlike generic multi-task settings with disjoint labels,…

Abstraction--the ability to recognize and distill essential computational patterns from complex problem statements--is a foundational skill in computer science, critical both for human problem-solvers and coding-oriented large language…

DeepRacer is a platform for end-to-end experimentation with RL and can be used to systematically investigate the key challenges in developing intelligent control systems. Using the platform, we demonstrate how a 1/18th scale car can learn…

It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown…

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL…

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…

Robots have to face challenging perceptual settings, including changes in viewpoint, lighting, and background. Current simulated reinforcement learning (RL) benchmarks such as DM Control provide visual input without such complexity, which…

We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an…

Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong potential in handling these challenges while remaining…

Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot achieve high decoding performance and low complexity…