相关论文: Imitation Learning for Generalizable Self-driving …

Hand-crafting generalised decision-making rules for real-world urban autonomous driving is hard. Alternatively, learning behaviour from easy-to-collect human driving demonstrations is appealing. Prior work has studied imitation learning…

Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data,…

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…

Deep imitation learning requires many expert demonstrations, which can be hard to obtain, especially when many tasks are involved. However, different tasks often share similarities, so learning them jointly can greatly benefit them and…

In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectories that distinguish…

Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to…

Robot planning is the process of selecting a sequence of actions that optimize for a task specific objective. The optimal solutions to such tasks are heavily influenced by the implicit structure in the environment, i.e. the configuration of…

Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical…

Deep Reinforcement Learning (RL) has been explored and verified to be effective in solving decision-making tasks in various domains, such as robotics, transportation, recommender systems, etc. It learns from the interaction with…

We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy…

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case of a robot operating in a real environment the…

In the field of Autonomous Driving, the system controlling the vehicle can be seen as an agent acting in a complex environment and thus naturally fits into the modern framework of Reinforcement Learning. However, learning to drive can be a…

The paper presents a complete pipeline for learning continuous motion control policies for a mobile robot when only a non-differentiable physics simulator of robot-terrain interactions is available. The multi-modal state estimation of the…

Learning robotic control policies in the real world gives rise to challenges in data efficiency, safety, and controlling the initial condition of the system. On the other hand, simulations are a useful alternative as they provide an…

Generalizing skill policies to novel conditions remains a key challenge in robot learning. Imitation learning methods, while data-efficient, are largely confined to the training region and consistently fail on input data outside it, leading…

Learning-based approaches, particularly reinforcement learning (RL), have become widely used for developing control policies for autonomous agents, such as locomotion policies for legged robots. RL training typically maximizes a predefined…

Imitation learning is a widely used policy learning method that enables intelligent agents to acquire complex skills from expert demonstrations. The input to the imitation learning algorithm is usually composed of both the current…

Robots are required to autonomously respond to changing situations. Imitation learning is a promising candidate for achieving generalization performance, and extensive results have been demonstrated in object manipulation. However,…

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…

A common strategy in modern learning systems is to learn a representation that is useful for many tasks, a.k.a. representation learning. We study this strategy in the imitation learning setting for Markov decision processes (MDPs) where…