Mix & Match Agent Curricula for Reinforcement Learning

Authors: Wojciech Czarnecki, Siddhant Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Nicolas Heess, Simon Osindero, Razvan Pascanu

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We now test and analyse our method on three sets of RL experiments. We train all agents with a form of batched actor critic with an off policy correction (Espeholt et al., 2018) using Deep Mind Lab (Beattie et al., 2016) as an environment suite.
Researcher Affiliation Industry 1Deep Mind, London, UK. Correspondence to: W Czarnecki <lejlot@google.com>, S Jayakumar <sidmj@google.com>.
Pseudocode No The paper describes its methods using prose, equations, and diagrams, but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code or include a link to a code repository for the methodology described.
Open Datasets Yes All agents with a form of batched actor critic with an off policy correction (Espeholt et al., 2018) using Deep Mind Lab (Beattie et al., 2016) as an environment suite.
Dataset Splits No The paper uses the Deep Mind Lab environment for experiments, which is an interactive environment rather than a static dataset. Therefore, it does not provide explicit training/validation/test dataset splits in the manner of supervised learning.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running its experiments.
Software Dependencies No The paper mentions environments and algorithms used (e.g., Deep Mind Lab, A3C), but it does not specify software dependencies with version numbers (e.g., specific versions of deep learning frameworks or programming languages).
Experiment Setup No The paper states that 'Full details of the experimental hyper-parameters can be found in the appendix', but these details are not present in the provided main text of the paper.