Extrapolating beyond-demonstrator (BD) performance through the imitation learning (IL) algorithm aims to learn from and subsequently outperform the demonstrator. To that end, a representative approach is to leverage inverse reinforcement learning (IRL) to infer a reward function from demonstrations before performing RL on the learned reward function. However, most existing reward extrapolation methods require massive demonstrations, making it difficult to be applied in tasks of limited training data. To address this problem, one simple solution is to perform data augmentation to artificially generate more training data, which may incur severe inductive bias and policy performance loss. In this paper, we propose a novel meta learning-based reward extrapolation (MLRE) algorithm, which can effectively approximate the ground-truth rewards using limited demonstrations. More specifically, MLRE first learns an initial reward function from a set of tasks that have abundant training data. Then the learned reward function will be fine-tuned using data of the target task. Extensive simulation results demonstrated that the proposed MLRE can achieve impressive performance improvement as compared to other similar BDIL algorithms.
University of Cambridge（剑桥大学）；University College London（伦敦大学学院）
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider multi-demonstrator offline RL, a middle ground where we know which demonstrators generated each dataset, but make no assumptions about the underlying policies of the demonstrators. This is the most natural setting when collecting data from multiple human operators, yet remains unexplored. Since different demonstrators induce different data distributions, we show that this can be naturally framed as a domain generali…
This work handles the inverse reinforcement learning (IRL) problem where only a small number of demonstrations are available from a demonstrator for each high-dimensional task, insufficient to estimate an accurate reward function. Observing that each demonstrator has an inherent reward for each state and the task-specific behaviors mainly depend on a small number of key states, we propose a meta IRL algorithm that first models the reward function for each task as a distribution conditioned on a baseline reward function shared by all tasks and dependent only on the demonstrator, and then finds …
National University of Defense Technology（国防科技大学）；International Digital Economy Academy（国际数字经济研究院）
In the last few years, the solution to Knowledge Graph (KG) completion via learning embeddings of entities and relations has attracted a surge of interest. Temporal KGs(TKGs) extend traditional Knowledge Graphs (KGs) by associating static triples with timestamps forming quadruples. Different from KGs and TKGs in the transductive setting, constantly emerging entities and relations in incomplete TKGs create demand to predict missing facts with unseen components, which is the extrapolation setting. Traditional temporal knowledge graph embedding (TKGE) methods are limited in the extrapolation sett…
The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow for better-than-demonstrator performance, preferences over demonstrations may be difficult to obtain, and little is known theoretically about when such methods can be expected to successfully extrapolate beyond the performance of the demonstrator. To address these issues, we first contribute a sufficient condition for better-than-demonstrator imitation learning and provide theoretical results showing why preferences…
Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing a…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Tufts University（塔夫茨大学）
Human gaze is known to be an intention-revealing signal in human demonstrations of tasks. In this work, we use gaze cues from human demonstrators to enhance the performance of agents trained via three popular imitation learning methods -- behavioral cloning (BC), behavioral cloning from observation (BCO), and Trajectory-ranked Reward EXtrapolation (T-REX). Based on similarities between the attention of reinforcement learning agents and human gaze, we propose a novel approach for utilizing gaze data in a computationally efficient manner, as part of an auxiliary loss function, which guides a net…
Warsaw University of Technology（华沙理工大学）；Institute of Science and Technology Austria (ISTA)（奥地利科学技术研究所（ISTA））
We introduce LIMES, a new method for learning with non-stationary streaming data, inspired by the recent success of meta-learning. The main idea is not to attempt to learn a single classifier that would have to work well across all occurring data distributions, nor many separate classifiers, but to exploit a hybrid strategy: we learn a single set of model parameters from which a specific classifier for any specific data distribution is derived via classifier adaptation. Assuming a multi-class classification setting with class-prior shift, the adaptation step can be performed analytically with …
Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally intractable for high-dimensional problems because each sample from the posterior requires solving an entire Markov Decision Process (MDP). While there exist non-Bayesian deep IRL methods, these methods typically infer point estimates of reward functions, precluding rigorous safety and uncertainty analysis. We propose Bayesian Reward Extrapolation (B-REX), a high…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Preferred Networks（首选网络）
A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal, rather than inferring the underlying intentions of the demonstrator that may have been poorly executed in practice. In this paper, we introduce a novel reward-learning-from-observation algorithm, Trajectory-ranked Reward EXtrapolation (T-REX), that extrapolates beyond a set of (approximately) ranked demonstrations in order to infer high-quality reward funct…
Georgia Institute of Technology（佐治亚理工学院）；Google（谷歌）
Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic platforms, but typical end-to-end learning is known for its poor extrapolation capability to new scenarios. Therefore, learning a navigation policy for a new robot with a new sensor configuration or a new target still remains a challenging problem. In this paper, we introduce a learning algorithm that enables rapid adaptation to new sensor configurations or ta…
AWS AI Labs（AWS人工智能实验室）；University of Southern California（南加州大学）
We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset (e.g., 5 samples per class) for extrapolation. This is because the log-performance error against the log-dataset size follows a nonlinear progression in the few-shot regime followed by a linear progression in the high-shot regime. We introduce a novel piecewise power law (PPL) that handles the two data regimes differently. To estimate the parameters of the PP…
Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）；Meituan（美团）
University of South Carolina（南卡罗来纳大学）；University of North Carolina Charlotte（北卡罗来纳大学夏洛特分校）
Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the cost of calculating the adsorption energies by DFT for a large number of reaction intermediates can become prohibitive. Here, we have identified appropriate descriptors and machine learning models that can be used to predict part of these adsorption energies given data on the rest of them. Our investigations also included the case when the species data used to train the predictive model is of…
Majorana Demonstrator Data Release for AI/ML Applications
Pacific Northwest National Laboratory（太平洋西北国家实验室）；University of South Carolina（南卡罗来纳大学）；Oak Ridge National Laboratory（橡树岭国家实验室）；National Research Center “Kurchatov Institute”（国家研究中心“库尔恰托夫研究所”）；University of South Dakota（南达科他大学）；University of North Carolina（北卡罗来纳大学）；Triangle Universities Nuclear Laboratory（三角大学核实验室）；North Carolina State University（北卡罗来纳州立大学）；Duke University（杜克大学）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；University of Washington（华盛顿大学）
Approaching Metaheuristic Deep Learning Combos for Automated Data Mining
Institute of Systems and Robotics, University of Coimbra（科英布拉大学系统与机器人研究所）；Department of Electrical and Computer Engineering, University of Coimbra（科英布拉大学电气与计算机工程学院）
