Interactive Imitation Learning (IIL) is a branch of Imitation Learning (IL) where human feedback is provided intermittently during robot execution allowing an online improvement of the robot's behavior. In recent years, IIL has increasingly started to carve out its own space as a promising data-driven alternative for solving complex robotic tasks. The advantages of IIL are its data-efficient, as the human feedback guides the robot directly towards an improved behavior, and its robustness, as the distribution mismatch between the teacher and learner trajectories is minimized by providing feedback directly over the learner's trajectories. Nevertheless, despite the opportunities that IIL presents, its terminology, structure, and applicability are not clear nor unified in the literature, slowing down its development and, therefore, the research of innovative formulations and discoveries. In this article, we attempt to facilitate research in IIL and lower entry barriers for new practitioners by providing a survey of the field that unifies and structures it. In addition, we aim to raise awareness of its potential, what has been accomplished and what are still open research questions. We organize the most relevant works in IIL in terms of human-robot interaction (i.e., types of feedback), interfaces (i.e., means of providing feedback), learning (i.e., models learned from feedback and function approximators), user experience (i.e., human perception about the learning process), applications, and benchmarks. Furthermore, we analyze similarities and differences between IIL and RL, providing a discussion on how the concepts offline, online, off-policy and on-policy learning should be transferred to IIL from the RL literature. We particularly focus on robotic applications in the real world and discuss their implications, limitations, and promising future areas of research.

Vertical federated learning (VFL) is a privacy-preserving machine learning paradigm that can learn models from features distributed on different platforms in a privacy-preserving way. Since in real-world applications the data may contain bias on fairness-sensitive features (e.g., gender), VFL models may inherit bias from training data and become unfair for some user groups. However, existing fair machine learning methods usually rely on the centralized storage of fairness-sensitive features to achieve model fairness, which are usually inapplicable in federated scenarios. In this paper, we propose a fair vertical federated learning framework (FairVFL), which can improve the fairness of VFL models. The core idea of FairVFL is to learn unified and fair representations of samples based on the decentralized feature fields in a privacy-preserving way. Specifically, each platform with fairness-insensitive features first learns local data representations from local features. Then, these local representations are uploaded to a server and aggregated into a unified representation for the target task. In order to learn a fair unified representation, we send it to each platform storing fairness-sensitive features and apply adversarial learning to remove bias from the unified representation inherited from the biased data. Moreover, for protecting user privacy, we further propose a contrastive adversarial learning method to remove private information from the unified representation in server before sending it to the platforms keeping fairness-sensitive features. Experiments on three real-world datasets validate that our method can effectively improve model fairness with user privacy well-protected.

In September 2016, Stanford's "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 17 study authors, each of whom is deeply rooted in AI research, chaired by Peter Stone of the University of Texas at Austin. The report, entitled "Artificial Intelligence and Life in 2030," examines eight domains of typical urban settings on which AI is likely to have impact over the coming years: transportation, home and service robots, healthcare, education, public safety and security, low-resource communities, employment and workplace, and entertainment. It aims to provide the general public with a scientifically and technologically accurate portrayal of the current state of AI and its potential and to help guide decisions in industry and governments, as well as to inform research and development in the field. The charge for this report was given to the panel by the AI100 Standing Committee, chaired by Barbara Grosz of Harvard University.

In recent years, reinforcement learning (RL) has shown great potential for solving tasks in well-defined environments like games or robotics. This paper aims to solve the robotic reaching task in a simulation run on the Neurorobotics Platform (NRP). The target position is initialized randomly and the robot has 6 degrees of freedom. We compare the performance of various state-of-the-art model-free algorithms. At first, the agent is trained on ground truth data from the simulation to reach the target position in only one continuous movement. Later the complexity of the task is increased by using image data as input from the simulation environment. Experimental results show that training efficiency and results can be improved with appropriate dynamic training schedule function for curriculum learning.

Reinforcement learning (rl) is a popular paradigm for sequential decision making problems. The past decade's advances in rl have led to breakthroughs in many challenging domains such as video games, board games, robotics, and chip design. The sample inefficiency of deep reinforcement learning methods is a significant obstacle when applying rl to real-world problems. Transfer learning has been applied to reinforcement learning such that the knowledge gained in one task can be applied when training in a new task. Curriculum learning is concerned with sequencing tasks or data samples such that knowledge can be transferred between those tasks to learn a target task that would otherwise be too difficult to solve. Designing a curriculum that improves sample efficiency is a complex problem. In this thesis, we propose a teacher-student curriculum learning setting where we simultaneously train a teacher that selects tasks for the student while the student learns how to solve the selected task. Our method is independent of human domain knowledge and manual curriculum design. We evaluated our methods on two reinforcement learning benchmarks: grid world and the challenging Google Football environment. With our method, we can improve the sample efficiency and generality of the student compared to tabula-rasa reinforcement learning.

Card game AI has always been a hot topic in the research of artificial intelligence. In recent years, complex card games such as Mahjong, DouDizhu and Texas Hold'em have been solved and the corresponding AI programs have reached the level of human experts. In this paper, we are devoted to developing an AI program for a more complex card game, GuanDan, whose rules are similar to DouDizhu but much more complicated. To be specific, the characteristics of large state and action space, long length of one episode and the unsure number of players in the GuanDan pose great challenges for the development of the AI program. To address these issues, we propose the first AI program DanZero for GuanDan using reinforcement learning technique. Specifically, we utilize a distributed framework to train our AI system. In the actor processes, we carefully design the state features and agents generate samples by self-play. In the learner process, the model is updated by Deep Monte-Carlo Method. After training for 30 days using 160 CPUs and 1 GPU, we get our DanZero bot. We compare it with 8 baseline AI programs which are based on heuristic rules and the results reveal the outstanding performance of DanZero. We also test DanZero with human players and demonstrate its human-level performance.

Cooperative multi-agent reinforcement learning (MARL) where a team of agents learn coordinated policies optimizing global team rewards has been extensively studied in recent years [25, 13], and find potential applications in a wide variety of domains like robot swarm control [15, 2], coordinating autonomous drivers [26, 41], network routing [38, 4], etc. Although cooperative MARL problems can be framed as a centralized single-agent, with the team as that actor with the joint action space, such an approach doesn't scale well. Joint action space grows exponentially with number of agents in such scenarios. Moreover, due to real world constraints on communication and observability, such framing is often not useful for a large number of real world applications. Unfortunately, simply independently learning decentralized policies based on local observations result into unstable learning and convergence issues due to non-stationarity from simultaneous exploration [12, 33]. This has resulted in MARL methods focusing on the centralized training decentralized execution (CTDE) paradigm, where during training decentralized polices can have access to extra state information during training but not during evaluation.

Abstract-- In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated transitions and an equivariant model that exploits the O(2) symmetry in robotic manipulation. Experimental evaluations demonstrate that our method can learn non-trivial manipulation tasks within ten demonstrations and outperforms the baselines with a significant margin.

Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert. Many algorithms for IRL have an inherently nested structure: the inner loop finds the optimal policy given parametrized rewards while the outer loop updates the estimates towards optimizing a measure of fit. For high dimensional environments such nested-loop structure entails a significant computational burden. To reduce the computational burden of a nested loop, novel methods such as SQIL [1] and IQ-Learn [2] emphasize policy estimation at the expense of reward estimation accuracy. However, without accurate estimated rewards, it is not possible to do counterfactual analysis such as predicting the optimal policy under different environment dynamics and/or learning new tasks. In this paper we develop a novel single-loop algorithm for IRL that does not compromise reward estimation accuracy. In the proposed algorithm, each policy improvement step is followed by a stochastic gradient step for likelihood maximization. We show that the proposed algorithm provably converges to a stationary solution with a finite-time guarantee. If the reward is parameterized linearly, we show the identified solution corresponds to the solution of the maximum entropy IRL problem. Finally, by using robotics control problems in MuJoCo and their transfer settings, we show that the proposed algorithm achieves superior performance compared with other IRL and imitation learning benchmarks.

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \textit{specify} and \textit{ground} these goals in such a way that we can both reliably reach goals during training as well as generalize to new goals during evaluation remains an open area of research. Defining goals in the space of noisy and high-dimensional sensory inputs poses a challenge for training goal-conditioned agents, or even for generalization to novel goals. We propose to address this by learning factorial representations of goals and processing the resulting representation via a discretization bottleneck, for coarser goal specification, through an approach we call DGRL. We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups, by experimentally evaluating this method on tasks ranging from maze environments to complex robotic navigation and manipulation. Additionally, we prove a theorem lower-bounding the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive combinatorial structure.