In this work we apply deep reinforcement learning to the problems of navigating a three-dimensional environment and inferring the locations of human speaker audio sources within, in the case where the only available information is the raw sound from the environment, as a simulated human listener placed in the environment would hear it. For this purpose we create two virtual environments using the Unity game engine, one presenting an audio-based navigation problem and one presenting an audio source localization problem. We also create an autonomous agent based on PPO online reinforcement learning algorithm and attempt to train it to solve these environments. Our experiments show that our agent achieves adequate performance and generalization ability in both environments, measured by quantitative metrics, even when a limited amount of training data are available or the environment parameters shift in ways not encountered during training. We also show that a degree of agent knowledge transfer is possible between the environments.
相關內容
We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things the environment's outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus, an agent's self-reflection ability can be numerically estimated by running the agent through a battery of extended environments. We are simultaneously releasing an open-source library of extended environments to serve as proof-of-concept of this technique. As the library is first-of-kind, we have avoided the difficult problem of optimizing it. Instead we have chosen environments with interesting properties. Some seem paradoxical, some lead to interesting thought experiments, some are even suggestive of how self-reflection might have evolved in nature. We give examples and introduce a simple transformation which experimentally seems to increase self-reflection.
This work studies the problem of image-goal navigation, which entails guiding robots with noisy sensors and controls through real crowded environments. Recent fruitful approaches rely on deep reinforcement learning and learn navigation policies in simulation environments that are much simpler in complexity than real environments. Directly transferring these trained policies to real environments can be extremely challenging or even dangerous. We tackle this problem with a hierarchical navigation method composed of four decoupled modules. The first module maintains an obstacle map during robot navigation. The second one predicts a long-term goal on the real-time map periodically. The third one plans collision-free command sets for navigating to long-term goals, while the final module stops the robot properly near the goal image. The four modules are developed separately to suit the image-goal navigation in real crowded scenarios. In addition, the hierarchical decomposition decouples the learning of navigation goal planning, collision avoidance and navigation ending prediction, which cuts down the search space during navigation training and helps improve the generalization to previously unseen real scenes. We evaluate the method in both a simulator and the real world with a mobile robot. The results show that our method outperforms several navigation baselines and can successfully achieve navigation tasks in these scenarios.
We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the robot to the target without relying on odometry or GPS at runtime. The system is learned by optimizing a combinational objective encompassing three key designs. First, we propose that an agent conceives the next observation before making an action decision. This is achieved by learning a variational generative module from expert demonstrations. We then propose predicting static collision in advance, as an auxiliary task to improve safety during navigation. Moreover, to alleviate the training data imbalance problem of termination action prediction, we also introduce a target checking module to differentiate from augmenting navigation policy with a termination action. The three proposed designs all contribute to the improved training data efficiency, static collision avoidance, and navigation generalization performance, resulting in a novel target-driven mapless navigation system. Through experiments on a TurtleBot, we provide evidence that our model can be integrated into a robotic system and navigate in the real world. Videos and models can be found in the supplementary material.
Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments show that our method is model-agnostic and can significantly improve the performance, the generalizability, and the training efficiency of current state-of-the-art navigation agents without increasing model complexity.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 6 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.
Reinforcement learning (RL) algorithms have been around for decades and been employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This paper addresses an important aspect of deep RL related to situations that demand multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multi-agent deep RL (MADRL) is presented, including non-stationarity, partial observability, continuous state and action spaces, multi-agent training schemes, multi-agent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed, with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to future development of more robust and highly useful multi-agent learning methods for solving real-world problems.
Neural machine translation requires large amounts of parallel training text to learn a reasonable-quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is not available. In this paper, we use monolingual linguistic resources in the source side to address this challenging problem based on a multi-task learning approach. More specifically, we scaffold the machine translation task on auxiliary tasks including semantic parsing, syntactic parsing, and named-entity recognition. This effectively injects semantic and/or syntactic knowledge into the translation model, which would otherwise require a large amount of training bitext. We empirically evaluate and show the effectiveness of our multi-task learning approach on three translation tasks: English-to-French, English-to-Farsi, and English-to-Vietnamese.
Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction
This paper introduces a novel neural network-based reinforcement learning approach for robot gaze control. Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision. The robot learns to focus its attention onto groups of people from its own audio-visual experiences, independently of the number of people, of their positions and of their physical appearances. In particular, we use a recurrent neural network architecture in combination with Q-learning to find an optimal action-selection policy; we pre-train the network using a simulated environment that mimics realistic scenarios that involve speaking/silent participants, thus avoiding the need of tedious sessions of a robot interacting with people. Our experimental evaluation suggests that the proposed method is robust against parameter estimation, i.e. the parameter values yielded by the method do not have a decisive impact on the performance. The best results are obtained when both audio and visual information is jointly used. Experiments with the Nao robot indicate that our framework is a step forward towards the autonomous learning of socially acceptable gaze behavior.
We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players' hidden states, in both cooperative and adversarial settings.
This paper presents a safety-aware learning framework that employs an adaptive model learning method together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use a sparse optimization technique, and the resulting model will be used in combination with control barrier certificates which constrain feedback controllers only when safety is about to be violated. Under some mild assumptions, solutions to the constrained feedback-controller optimization are guaranteed to be globally optimal, and the monotonic improvement of a feedback controller is thus ensured. In addition, we reformulate the (action-)value function approximation to make any kernel-based nonlinear function estimation method applicable. We then employ a state-of-the-art kernel adaptive filtering technique for the (action-)value function approximation. The resulting framework is verified experimentally on a brushbot, whose dynamics is unknown and highly complex.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191