arXiv subjects

Keith W. Ross

Publications and source records attributed to Keith W. Ross.

9 recordsLinked to original sources

arXiv2026

PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning

Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer across embodiments. Precise IK remains laborious: redundancy and singularities complicate the inverse mapping, execution depends on hand-tuned controllers, and training data on physical robots are costly to collect. We present PolicyIK, a goal-conditioned reinforcement learning policy for high-precision IK. It updates joint-position references from pose feedback and observes its accumulated reference relative to the measured joints, so it can retain the offset that the position controller needs at rest. Two-scale pose errors with an error-dependent action gain resolve millimeter residuals while preserving large motions. Progress and dwell rewards teach it to both reach the tolerance and stay within it. In simulation, a single attempt by the trained PPO policy keeps the mean errors over the final second within 1 mm and 0.2° on 93.5% of held-out tasks, and a deployment protocol raises success to 98.9%. When trained directly on a physical arm with an off-policy RL learner, PolicyIK achieves higher reaching and holding success than all four classical IK controllers under the same time budgets. In simulated pick-and-place, PolicyIK executes the end-effector commands of the $π_{0.5}$ VLA policy with 95.7% success. These results show that reinforcement learning can provide high-precision inverse kinematics for robot arms. Code is available at https://github.com/Tinaliu0123/PolicyIK.

cs.RO↗

arXiv2026

Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry

Counting is a simple task on which transformers can nevertheless fail at long sequence lengths. We study the cost of counting in a single attention layer, up to a maximum length $L$, focusing on how softmax attention and layer normalization shape the representation from which the count is recovered. We mainly focus on regression read-out but also consider classification read-out. For regression, we show unnormalized linear attention counts exactly at parameter norms independent of $L$. For softmax attention, regression cannot count exactly with finite parameters; it recovers the count after rounding, but only when the vector parameter norms grow with $L$. We measure this cost by $B_{\min}$, the smallest bound that can be placed on every trainable vector to ensure exact counting after rounding, and derive tight rates. At fixed model dimension, $B_{\min}$ grows as $L$ without normalization, as $L^{3/2}$ under bare post-normalization, and as $L^{3/4}$ with learned post-normalization. The last rate is unexpected: post-normalization discards the magnitude that carries the count and might be expected to make counting harder, yet with a learnable gain it counts at a smaller norm than softmax without normalization. Bare pre-normalization is different: it bounds the attention scores, so beyond a finite length no parameter norm suffices. A classification read-out keeps every norm bounded under every placement, but a dense head stores one output vector per count and costs more in storage. Experiments on the post-normalized model reproduce this split between the two read-outs. Together, our theoretical and empirical findings characterize how self-attention, layer-normalization placement, and read-out choice shape the representation geometry and parameter cost of counting in the minimal single-head architecture studied here.

cs.LG↗

arXiv2022

Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance

Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization. In this paper, we propose a novel model-free algorithm, Aggressive Q-Learning with Ensembles (AQE), which improves the sample-efficiency performance of REDQ and the asymptotic performance of TQC, thereby providing overall state-of-the-art performance during all stages of training. Moreover, AQE is very simple, requiring neither distributional representation of critics nor target randomization. The effectiveness of AQE is further supported by our extensive experiments, ablations, and theoretical results.

cs.LG↗

arXiv2021

On-Policy Deep Reinforcement Learning for the Average-Reward Criterion

We develop theory and algorithms for average-reward on-policy Reinforcement Learning (RL). We first consider bounding the difference of the long-term average reward for two policies. We show that previous work based on the discounted return (Schulman et al., 2015; Achiam et al., 2017) results in a non-meaningful bound in the average-reward setting. By addressing the average-reward criterion directly, we then derive a novel bound which depends on the average divergence between the two policies and Kemeny's constant. Based on this bound, we develop an iterative procedure which produces a sequence of monotonically improved policies for the average reward criterion. This iterative procedure can then be combined with classic DRL (Deep Reinforcement Learning) methods, resulting in practical DRL algorithms that target the long-run average reward criterion. In particular, we demonstrate that Average-Reward TRPO (ATRPO), which adapts the on-policy TRPO algorithm to the average-reward criterion, significantly outperforms TRPO in the most challenging MuJuCo environments.

cs.LG↗

arXiv2020

First Order Constrained Optimization in Policy Space

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of behavior-such as ones which are deemed unsafe and to be avoided-are best captured through constraints. We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent's overall reward while ensuring the agent satisfies a set of cost constraints. Using data generated from the current policy, FOCOPS first finds the optimal update policy by solving a constrained optimization problem in the nonparameterized policy space. FOCOPS then projects the update policy back into the parametric policy space. Our approach has an approximate upper bound for worst-case constraint violation throughout training and is first-order in nature therefore simple to implement. We provide empirical evidence that our simple approach achieves better performance on a set of constrained robotics locomotive tasks.

cs.LG↗

arXiv2018

Supervised Policy Update for Deep Reinforcement Learning

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 non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized optimization problem. We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology. The SPU implementation is much simpler than TRPO. In terms of sample efficiency, our extensive experiments show SPU outperforms TRPO in Mujoco simulated robotic tasks and outperforms PPO in Atari video game tasks.

cs.LG↗

arXiv2018

Efficient Entropy for Policy Gradient with Multidimensional Action Space

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This paper considers entropy bonus, which is used to encourage exploration in policy gradient. In the case of high-dimensional action spaces, calculating the entropy and its gradient requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible. We develop several novel unbiased estimators for the entropy bonus and its gradient. We apply these estimators to several models for the parameterized policies, including Independent Sampling, CommNet, Autoregressive with Modified MDP, and Autoregressive with LSTM. Finally, we test our algorithms on two environments: a multi-hunter multi-rabbit grid game and a multi-agent multi-arm bandit problem. The results show that our entropy estimators substantially improve performance with marginal additional computational cost.

cs.LG↗

arXiv2017

Mining Anonymity: Identifying Sensitive Accounts on Twitter

We explore the feasibility of automatically finding accounts that publish sensitive content on Twitter. One natural approach to this problem is to first create a list of sensitive keywords, and then identify Twitter accounts that use these words in their tweets. But such an approach may overlook sensitive accounts that are not covered by the subjective choice of keywords. In this paper, we instead explore finding sensitive accounts by examining the percentage of anonymous and identifiable followers the accounts have. This approach is motivated by an earlier study showing that sensitive accounts typically have a large percentage of anonymous followers and a small percentage of identifiable followers. To this end, we first considered the problem of automatically determining if a Twitter account is anonymous or identifiable. We find that simple techniques, such as checking for name-list membership, perform poorly. We designed a machine learning classifier that classifies accounts as anonymous or identifiable. We then classified an account as sensitive based on the percentages of anonymous and identifiable followers the account has. We applied our approach to approximately 100,000 accounts with 404 million active followers. The approach uncovered accounts that were sensitive for a diverse number of reasons. These accounts span across varied themes, including those that are not commonly proposed as sensitive or those that relate to socially stigmatized topics. To validate our approach, we applied Latent Dirichlet Allocation (LDA) topic analysis to the tweets in the detected sensitive and non-sensitive accounts. LDA showed that the sensitive and non-sensitive accounts obtained from the methodology are tweeting about distinctly different topics. Our results show that it is indeed possible to objectively identify sensitive accounts at the scale of Twitter.

cs.SI↗

arXiv2011

I Know Where You are and What You are Sharing: Exploiting P2P Communications to Invade Users' Privacy

In this paper, we show how to exploit real-time communication applications to determine the IP address of a targeted user. We focus our study on Skype, although other real-time communication applications may have similar privacy issues. We first design a scheme that calls an identified targeted user inconspicuously to find his IP address, which can be done even if he is behind a NAT. By calling the user periodically, we can then observe the mobility of the user. We show how to scale the scheme to observe the mobility patterns of tens of thousands of users. We also consider the linkability threat, in which the identified user is linked to his Internet usage. We illustrate this threat by combining Skype and BitTorrent to show that it is possible to determine the file-sharing usage of identified users. We devise a scheme based on the identification field of the IP datagrams to verify with high accuracy whether the identified user is participating in specific torrents. We conclude that any Internet user can leverage Skype, and potentially other real-time communication systems, to observe the mobility and file-sharing usage of tens of millions of identified users.

cs.NI↗