Diversification of Adaptive Policy for Effective Offline Reinforcement Learning

Authors: Yunseon Choi, Li Zhao, Chuheng Zhang, Lei Song, Jiang Bian, Kee-Eung Kim

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate Mo DAP through experiments on the D4RL and Neo RL benchmarks, showcasing its performance superiority over state-of-the-art algorithms.
Researcher Affiliation Collaboration 1KAIST AI 2Microsoft Research Asia
Pseudocode Yes Algorithm 1 Mo DAP
Open Source Code No The paper does not provide any explicit statements or links indicating the availability of its source code.
Open Datasets Yes We evaluate Mo DAP through experiments on the D4RL [Fu et al., 2020] and Neo RL [Qin et al., 2022] benchmarks
Dataset Splits Yes In the initial phase of pre-training the dynamics models, we divide the offline dataset into a training set and a validation set using an 8:2 ratio.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments, such as GPU or CPU models.
Software Dependencies No The paper mentions using SAC and GRU but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes In the initial phase of pre-training the dynamics models, we divide the offline dataset into a training set and a validation set using an 8:2 ratio. For each task, we construct a set of estimated models by training either 7 (for D4RL) or 15 (for Neo RL) models. After this training, we proceed to select the top 5 (for D4RL) or 10 (for Neo RL) models based on their predictive accuracy, which is evaluated on the validation set.