相关论文: Efficient Active Imitation Learning with Random Ne…

Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind of imitation…

Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced…

Deep reinforcement learning suffers from catastrophic forgetting and sample inefficiency making it less applicable to the ever-changing real world. However, the ability to use previously learned knowledge is essential for AI agents to…

Deep learning models are vulnerable to adversarial examples, posing critical security challenges in real-world applications. While Adversarial Training (AT ) is a widely adopted defense mechanism to enhance robustness, it often incurs a…

The reward model (RM), as the core component of reinforcement learning from human feedback (RLHF) for large language models (LLMs), responsible for providing reward signals to generated responses. However, the mainstream discriminative…

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and…

Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is…

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…

Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…

Adversarial distillation (AD) is a knowledge distillation technique that facilitates the transfer of robustness from teacher deep neural network (DNN) models to lightweight target (student) DNN models, enabling the target models to perform…

Recently, diffusion policy has shown impressive results in handling multi-modal tasks in robotic manipulation. However, it has fundamental limitations in out-of-distribution failures that persist due to compounding errors and its limited…

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand,…

Adversarial training is the most promising method for learning robust models against adversarial examples. A recent study has shown that knowledge distillation between the same architectures is effective in improving the performance of…

Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…

When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail. In this paper, we propose a simple yet new and efficient solution to this problem. We assume that, in the undelayed environment,…

Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed…