Related papers: Periodic Intra-Ensemble Knowledge Distillation for…
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary…
Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to…
Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…
Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…
We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…
Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in…
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…
Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…
Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to the real world in a zero-shot setting. However, a huge…
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…
Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…
Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…
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…
Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with…
Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL)…
Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…
Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels,…
We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards…