Existing off-policy reinforcement learning algorithms often rely on an explicit state-action-value function representation, which can be problematic in high-dimensional action spaces due to the curse of dimensionality. This reliance results in data inefficiency as maintaining a state-action-value function in such spaces is challenging. We present an efficient approach that utilizes only a state-value function as the critic for off-policy deep reinforcement learning. This approach, which we refer to as Vlearn, effectively circumvents the limitations of existing methods by eliminating the necessity for an explicit state-action-value function. To this end, we leverage a weighted importance sampling loss for learning deep value functions from off-policy data. While this is common for linear methods, it has not been combined with deep value function networks. This transfer to deep methods is not straightforward and requires novel design choices such as robust policy updates, twin value function networks to avoid an optimization bias, and importance weight clipping. We also present a novel analysis of the variance of our estimate compared to commonly used importance sampling estimators such as V-trace. Our approach improves sample complexity as well as final performance and ensures consistent and robust performance across various benchmark tasks. Eliminating the state-action-value function in Vlearn facilitates a streamlined learning process, yielding high-return agents.

Robotic manipulation in cluttered environments presents significant challenges, particularly when the clutter includes thin, deformable objects like cables, which complicate perception and decision-making processes. In the context of datacenters, the automation of networking tasks often involves the manipulation of optical transceivers within densely packed cable configurations. Such environments are characterized by an abundance of delicate, overlapping, and intersecting cables, leading to frequent occlusions. This paper introduces an innovative system designed for the manipulation of optical transceivers in environments cluttered by cables. Our integrated approach combines advanced 3D scene understanding with a heuristic-based pushing policy to effectively manipulate optical transceivers amidst clutter. The system's perception component utilizes image segmentation and 3D reconstruction to accurately model the transceivers and surrounding cables. Meanwhile, the planning aspect employs a search algorithm with task-specific heuristics, to navigate the gripper, displace obstructing cables, and safely achieve a precise pre-grasp position in front of the target transceiver. We have conducted extensive evaluations of our methodology in both simulated and real-world settings, demonstrating its high success rates, robustness, and proficiency in addressing the unique challenges posed by cable-occluded environments within datacenters.

We present the B-spline Encoded Action Sequence Tokenizer (BEAST), a novel action tokenizer that encodes action sequences into compact discrete or continuous tokens using B-splines. In contrast to existing action tokenizers based on vector quantization or byte pair encoding, BEAST requires no separate tokenizer training and consistently produces tokens of uniform length, enabling fast action sequence generation via parallel decoding. Leveraging our B-spline formulation, BEAST inherently ensures generating smooth trajectories without discontinuities between adjacent segments. We extensively evaluate BEAST by integrating it with three distinct model architectures: a Variational Autoencoder (VAE) with continuous tokens, a decoder-only Transformer with discrete tokens, and Florence-2, a pretrained Vision-Language Model with an encoder-decoder architecture, demonstrating BEAST's compatibility and scalability with large pretrained models. We evaluate BEAST across three established benchmarks consisting of 166 simulated tasks and on three distinct robot settings with a total of 8 real-world tasks. Experimental results demonstrate that BEAST (i) significantly reduces both training and inference computational costs, and (ii) consistently generates smooth, high-frequency control signals suitable for continuous control tasks while (iii) reliably achieves competitive task success rates compared to state-of-the-art methods.

Current advancements in reinforcement learning (RL) have predominantly focused on learning step-based policies that generate actions for each perceived state. While these methods efficiently leverage step information from environmental interaction, they often ignore the temporal correlation between actions, resulting in inefficient exploration and unsmooth trajectories that are challenging to implement on real hardware. Episodic RL (ERL) seeks to overcome these challenges by exploring in parameters space that capture the correlation of actions. However, these approaches typically compromise data efficiency, as they treat trajectories as opaque black boxes. In this work, we introduce a novel ERL algorithm, Temporally-Correlated Episodic RL (TCE), which effectively utilizes step information in episodic policy updates, opening the 'black box' in existing ERL methods while retaining the smooth and consistent exploration in parameter space. TCE synergistically combines the advantages of step-based and episodic RL, achieving comparable performance to recent ERL methods while maintaining data efficiency akin to state-of-the-art (SoTA) step-based RL.

In recent years, there have been a rising number of legislative efforts and proposed technical measures to weaken privacy-preserving technology, with the stated goal of countering serious crimes like child abuse. One of these proposed measures is Client-Side Scanning (CSS). CSS has been hotly debated both in the context of Apple stating their intention to deploy it in 2021 as well as EU legislation being proposed in 2022. Both sides of the argument state that they are working in the best interests of the people. To shed some light on this, we conducted a survey with a representative sample of German citizens. We investigated the general acceptance of CSS vs cloud-based scanning for different types of crimes and analyzed how trust in the German government and companies such as Google and Apple influenced our participants’ views. We found that, by and large, the majority of participants were willing to accept CSS measures to combat serious crimes such as child abuse or terrorism, but support dropped significantly for other illegal activities. However, the majority of participants who supported CSS were also worried about potential abuse, with only 20% stating that they were not concerned. These results suggest that many of our participants would be willing to have their devices scanned and accept some risks in the hope of aiding law enforcement. In our analysis, we argue that there are good reasons to not see this as a carte blanche for the introduction of CSS but as a call to action for the S&P community. More research is needed into how a population’s desire to prevent serious crime online can be achieved while mitigating the risks to privacy and society.