相关论文: Cross-Domain Imitation Learning via Optimal Transp…

Interactive Imitation Learning (IIL) allows agents to acquire desired behaviors through human interventions, but current methods impose high cognitive demands on human supervisors. We propose the Adaptive Intervention Mechanism (AIM), a…

Generative adversarial imitation learning (GAIL) demonstrates tremendous success in practice, especially when combined with neural networks. Different from reinforcement learning, GAIL learns both policy and reward function from expert…

Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge. Traditional imitation learning methods usually fail in this task because most of them are designed to learn one specific behavior…

We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL using a hierarchical model to enable generalization to…

Generative Adversarial Imitation Learning (GAIL) trains a generative policy to mimic a demonstrator. It uses on-policy Reinforcement Learning (RL) to optimize a reward signal derived from a GAN-like discriminator. A major drawback of GAIL…

While it is relatively easier to train humanoid robots to mimic specific locomotion skills, it is more challenging to learn from various motions and adhere to continuously changing commands. These robots must accurately track motion…

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding…

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly…

Imitation learning is an effective tool for robotic learning tasks where specifying a reinforcement learning (RL) reward is not feasible or where the exploration problem is particularly difficult. Imitation, typically behavior cloning or…

Generative Adversarial Imitation Learning (GAIL) can learn policies without explicitly defining the reward function from demonstrations. GAIL has the potential to learn policies with high-dimensional observations as input, e.g., images. By…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools.…

This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation…

Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…

Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons,…

We address the problem of imitation learning with multi-modal demonstrations. Instead of attempting to learn all modes, we argue that in many tasks it is sufficient to imitate any one of them. We show that the state-of-the-art methods such…

In this paper, we present a new idea for Transfer Learning (TL) based on Gibbs Sampling. Gibbs sampling is an algorithm in which instances are likely to transfer to a new state with a higher possibility with respect to a probability…

Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which…

Imitation learning (IL) enables agents to acquire skills by observing and replicating the behavior of one or multiple experts. In recent years, advances in deep learning have significantly expanded the capabilities and scalability of…

Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly applied for learning such representations from data, but they…