Article-Journal

We propose a variational dynamic model based on the conditional variational inference to model the multimodality and stochasticity.

We analyze the hindsight bias due to this use of hindsight goals and propose the bias-corrected HER (BHER), an efficient algorithm that corrects the hindsight bias in training.

We conduct a comprehensive survey on existing exploration methods for both single-agent RL and multiagent RL.

We propose monotonic quantile network (MQN) with conservative quantile regression (CQR) for risk-averse policy learning.

We present an offline RL algorithm that combines hindsight relabeling and supervised regression to predict actions without oracle information.

We introduce a novel strategy employing diverse randomized value functions to estimate the posterior distribution of Q-values.

We propose an uncertainty-based MTDS approach that shares the entire dataset without data selection.

Our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning.

We propose the Robust Offline-to-Online (RO2O) algorithm, designed to enhance offline policies through uncertainty and smoothness, and to mitigate the performance drop in online adaptation.

We propose a novel Dynamic Skill Learning (DSL) framework to enable more effective adaptation and collaboration in complex tasks.