Related papers: Adversarial Imitation Learning with General Functi…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…

Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvements: it beats the classical approach Behavioral Cloning (BC)…

Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in…

The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear…

Due to its empirical success in few-shot classification and reinforcement learning, meta-learning has recently received significant interest. Meta-learning methods leverage data from previous tasks to learn a new task in a sample-efficient…

Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to…

We formulate the problem of learning to imitate multiple, non-deterministic teachers with minimal interaction cost. Rather than learning a specific policy as in standard imitation learning, the goal in this problem is to learn a…

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible. However, standard IL methods implicitly assume that the environment dynamics…

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this…

Many tasks in practice require the collaboration of multiple agents through reinforcement learning. In general, cooperative multiagent reinforcement learning algorithms can be classified into two paradigms: Joint Action Learners (JALs) and…

Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications of CIL methods are twofold: (1) non-i.i.d batch streams and…

Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data…

While reinforcement learning (RL) has shown promising performance, its sample complexity continues to be a substantial hurdle, restricting its broader application across a variety of domains. Imitation learning (IL) utilizes oracles to…

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby…

Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The…

Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a…