We propose a novel approach to learn goal-conditioned policies for locomotion in a batch RL setting. The batch data is collected by a policy that is not goal-conditioned. For the locomotion task, this translates to data collection using a policy learnt by the agent for walking straight in one direction, and using that data to learn a goal-conditioned policy that enables the agent to walk in any direction. The data collection policy used should be invariant to the direction the agent is facing i.e. regardless of its initial orientation, the agent should take the same actions to walk forward. We exploit this property to learn a goal-conditioned policy using two key ideas: (1) augmenting data by generating trajectories with the same actions in different directions, and (2) learning an encoder that enforces invariance between these rotated trajectories with a Siamese framework. We show that our approach outperforms existing RL algorithms on 3-D locomotion agents like Ant, Humanoid and Minitaur.
DeepMind（深度思考）；Princeton University（普林斯顿大学）；University of Alberta（阿尔伯塔大学）
This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that sparsity-aware methods can make batch RL more sample efficient. We first consider the off-policy policy evaluation problem. To evaluate a new target policy, we analyze a Lasso fitted Q-evaluation method and establish a finite-sample error bound that has no polynomial dependence on the ambient dimension. To reduce the Lasso bias, we further propose a post model-sele…
Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
Department of Computer Science, University of Toronto, Toronto, Canada（多伦多大学计算机科学系）；Vector Institute, Toronto, Canada（向量研究所）；University of Texas at Austin, Austin, USA（德克萨斯大学奥斯汀分校）；Harvard University, Cambridge, USA（哈佛大学）
This paper investigates methods for estimating the optimal stochastic control policy for a Markov Decision Process with unknown transition dynamics and an unknown reward function. This form of model-free reinforcement learning comprises many real world systems such as playing video games, simulated control tasks, and real robot locomotion. Existing methods for estimating the optimal stochastic control policy rely on high variance estimates of the policy descent. However, these methods are not guaranteed to find the optimal stochastic policy, and the high variance gradient estimates make conver…
PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion
Laboratory of Automation and Robotics (LAR) in the Department of Electrical & Computer Engineering, University of Patras（自动化与机器人实验室（LAR）（电气与计算机工程系，帕特拉斯大学））；Archimedes/Athena RC, Greece（阿基米德/雅典娜RC，希腊）；Athena - Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece（雅典娜信息、通信和知识技术研究中心（Xanthi，希腊））；Computational Intelligence Laboratory (CILab), Department of Mathematics, University of Patras（计算智能实验室（CILab）（数学系，帕特拉斯大学））
Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California San Diego（加州大学圣地亚哥分校）；MBZUAI（马克斯·普朗克人工智能研究所）；University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）
本文针对目标条件强化学习在以对象为中心领域中的稀疏奖励问题，提出基于零反事实交互定义的 HInt 事后重新标记方法和 NCII 交互推断模型，显著提升交互推断准确率并将样本效率提高最多 4 倍。
Kyushu Institute of Technology（九州工业大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）
Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse solutions is beneficial because diversity enables robust few-shot adaptation. Although existing methods learn diverse solutions by using the mutual information as unsupervised rewards, such an approach often suffers from the bias of the gradient estimator induced by value function approximation. In this study, we propose a novel method that can learn diverse solutions without suffering the bia…
Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）；ETH Zurich（苏黎世联邦理工学院）；University of Edinburgh（爱丁堡大学）；University of California Los Angeles（加利福尼亚大学洛杉矶分校）
Human-AI shared control allows human to interact and collaborate with AI to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempt the goal-conditioned design to achieve human-controllable policies at the cost of redesigning the reward function and training paradigm. Inspired by the neuroscience approach to investigate the motor cortex in primates, we develop a simple yet effective frequency-based approach called \textit{Policy Dissection} to align the intermediate representation of the learned neural controller with the kinematic attributes of t…
Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is large. Searching in a large goal space poses difficulty for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a $k$-step adjacent region of the current state using an adjacency constrain…
Goal-conditioned reinforcement learning for ultrasound navigation guidance
King’s College London（伦敦国王学院）；Siemens Healthcare Limited（西门子医疗有限公司）；Siemens Healthineers（西门子医疗）；Siemens Healthineers AG（西门子医疗股份公司）；Carol Davila University of Medicine and Pharmacy Bucharest（布加勒斯特卡罗尔·达维拉医药大学）；Fortis Institute of Medical Sciences（富蒂斯医学院）；Guy’s and St Thomas’ NHS Foundation Trust（盖伊和圣托马斯国民保健信托基金）
Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal navigation policies. FollowNet maps natural language instructions as well as visual and depth inputs to locomotion primitives. FollowNet processes instructions using an attention mechanism conditioned on its visual and depth input to focus on the relevant parts of the command while performing the navigation task. Deep reinforcement learning (RL) a sparse reward learns simultaneo…
We present a new approach for transfer of dynamic robot control policies such as biped locomotion from simulation to real hardware. Key to our approach is to perform system identification of the model parameters μ of the hardware (e.g. friction, center-of-mass) in two distinct stages, before policy learning (pre-sysID) and after policy learning (post-sysID). Pre-sysID begins by collecting trajectories from the physical hardware based on a set of generic motion sequences. Because the trajectories may not be related to the task of interest, presysID does not attempt to accurately identify the tr…
UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
Department of Chemical Engineering, Norwegian University of Science and Technology (NTNU)（化学工程系，挪威科学与技术大学）；Department of Computing, Imperial College London（计算系，帝国理工学院伦敦分校）
University of Maryland, College Park（马里兰大学帕克分校）；Georgetown University（乔治城大学）
This paper considers the multi-agent distributed linear least-squares problem. The system comprises multiple agents, each agent with a locally observed set of data points, and a common server with whom the agents can interact. The agents' goal is to compute a linear model that best fits the collective data points observed by all the agents. In the server-based distributed settings, the server cannot access the data points held by the agents. The recently proposed Iteratively Pre-conditioned Gradient-descent (IPG) method has been shown to converge faster than other existing distributed algorith…
