Policy-Independent Behavioral Metric-Based Representation for Deep Reinforcement Learning

Authors: Weijian Liao, Zongzhang Zhang, Yang Yu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our approach on Deep Mind control tasks with default and distracting backgrounds. By statistically reliable evaluation protocols, our experiments demonstrate our approach is superior to previous metric-based methods in terms of sample efficiency and asymptotic performance in both backgrounds.
Researcher Affiliation Academia 1 National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China 2 Peng Cheng Laboratory, Shenzhen, 518055, China
Pseudocode No The paper does not contain any clearly labeled
Open Source Code No The paper states:
Open Datasets Yes We conduct experiments on the Deep Mind Control Suite (Tassa et al. 2018)... we randomly sample multiple videos from the kinetics dataset (Kay et al. 2017) as background...
Dataset Splits No The paper describes evaluation protocols (e.g., IQM normalized score) and the number of runs (10 seeds for 8 tasks) but does not provide specific train/validation/test dataset splits (e.g., percentages or sample counts) needed for reproduction.
Hardware Specification No The paper states:
Software Dependencies No The paper refers to various algorithms and frameworks (e.g., SAC, Q-learning, DDPG, TD3) but does not provide specific version numbers for any software dependencies like programming languages or libraries (e.g., Python version, TensorFlow/PyTorch version).
Experiment Setup No The paper mentions that