相关论文: Driving Beyond Privilege: Distilling Dense-Reward …

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

The problem of learning from few labeled examples while using large amounts of unlabeled data has been approached by various semi-supervised methods. Although these methods can achieve superior performance, the models are often not…

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting…

Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance. Motivated by this gap, we empirically study how misalignment between…

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the…

On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher model should be used,…

Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which…

This paper deals with robotic lever control using Explainable Deep Reinforcement Learning. First, we train a policy by using the Deep Deterministic Policy Gradient algorithm and the Hindsight Experience Replay technique, where the goal is…

Conventionally, supervised fine-tuning (SFT) is treated as a simple imitation learning process that only trains a policy to imitate expert behavior on demonstration datasets. In this work, we challenge this view by establishing a…

The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural…

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…

We introduce Self-supervised Online Reward Shaping (SORS), which aims to improve the sample efficiency of any RL algorithm in sparse-reward environments by automatically densifying rewards. The proposed framework alternates between…

We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite…

When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…