Boyan Li

Tong Sang, Hongyao Tang, Yi Ma et al.

Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios. Although advances have been made recently, most prior works assume sufficient online interaction on training environments, which can be costly in practical cases. To this end, we focus on an offline-training-online-adaptation setting, in which the agent first learns from offline experiences collected in environments with different dynamics and then performs online policy adaptation in environments with new dynamics. In this paper, we propose Policy Adaptation with Decoupled Representations (PAnDR) for fast policy adaptation. In offline training phase, the environment representation and policy representation are learned through contrastive learning and policy recovery, respectively. The representations are further refined by mutual information optimization to make them more decoupled and complete. With learned representations, a Policy-Dynamics Value Function (PDVF) [Raileanu et al., 2020] network is trained to approximate the values for different combinations of policies and environments from offline experiences. In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF. Our experiments show that PAnDR outperforms existing algorithms in several representative policy adaptation problems.

Boyan Li, Yongting Chen, Dayou Zhang et al.

Volumetric video streaming offers immersive 3D experiences but faces significant challenges due to high bandwidth requirements and latency issues in transmitting detailed content in real time. Traditional methods like point cloud streaming compromise visual quality when zoomed in, and neural rendering techniques are too computationally intensive for real-time use. Though mesh-based streaming stands out by preserving surface detail and connectivity, offering a more refined representation for 3D content, traditional mesh streaming methods typically transmit data on a per-frame basis, failing to take full advantage of temporal redundancies across frames. This results in inefficient bandwidth usage and poor adaptability to fluctuating network conditions. We introduce Deformation-based Adaptive Volumetric Video Streaming, a novel framework that enhances volumetric video streaming performance by leveraging the inherent deformability of mesh-based representations. DeformStream uses embedded deformation to reconstruct subsequent frames from inter-frame motion, significantly reducing bandwidth usage while ensuring visual coherence between frames. To address frame reconstruction overhead and network adaptability, we formulate a new QoE model that accounts for client-side deformation latency and design a dynamic programming algorithm to optimize the trade-off between visual quality and bandwidth consumption under varying network conditions. Our evaluation demonstrates that Deformation-based Adaptive Volumetric Video Streaming outperforms existing mesh-based streaming systems in both bandwidth efficiency and visual quality, offering a robust solution for real-time volumetric video applications.

Boyan Li, Hongyao Tang, Yan Zheng et al.

Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to address hybrid action RL is to convert the hybrid action space into a unified homogeneous action space by discretization or continualization, so that conventional RL algorithms can be applied. However, this ignores the underlying structure of hybrid action space and also induces the scalability issue and additional approximation difficulties, thus leading to degenerated results. In this paper, we propose Hybrid Action Representation (HyAR) to learn a compact and decodable latent representation space for the original hybrid action space. HyAR constructs the latent space and embeds the dependence between discrete action and continuous parameter via an embedding table and conditional Variantional Auto-Encoder (VAE). To further improve the effectiveness, the action representation is trained to be semantically smooth through unsupervised environmental dynamics prediction. Finally, the agent then learns its policy with conventional DRL algorithms in the learned representation space and interacts with the environment by decoding the hybrid action embeddings to the original action space. We evaluate HyAR in a variety of environments with discrete-continuous action space. The results demonstrate the superiority of HyAR when compared with previous baselines, especially for high-dimensional action spaces.