We introduce a value-based RL agent, which we call BBF, that achieves super-human
performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used …

Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of
the world. However, if initialized with knowledge of high-level subgoals and transitions …

A growing body of evidence suggests that neural networks employed in deep reinforcement
learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the …

Knowledge distillation is commonly used for compressing neural networks to reduce their
inference cost and memory footprint. However, current distillation methods for auto …

Learning to solve tasks from a sparse reward signal is a major challenge for standard
reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to …

We consider solving sequential decision-making problems in the scenario where the agent
has access to two supervision sources: $\textit {reward signal} $ and a $\textit {teacher} …

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining
and online finetuning, promises enhanced sample efficiency and policy performance …

Collaborative vehicle routing occurs when carriers collaborate through sharing their
transportation requests and performing transportation requests on behalf of each other. This …

Recent progress on vision-language foundation models have brought significant
advancement to building general-purpose robots. By using the pre-trained models to …

In many Reinforcement Learning (RL) papers, learning curves are useful indicators to
measure the effectiveness of RL algorithms. However, the complete raw data of the learning …