Robustly Learning Composable Options in Deep Reinforcement Learning
Authors: Akhil Bagaria, Jason Senthil, Matthew Slivinski, George Konidaris
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test these improvements on four sparse-reward maze navigation tasks involving a simulated quadrupedal robot. Each method successively improves the robustness of a baseline skill discovery method, substantially outperforming state-of-the-art flat and hierarchical methods. |
| Researcher Affiliation | Academia | Department of Computer Science, Brown University {akhil bagaria, jason senthil, matthew slivinski}@brown.edu, gdk@cs.brown.edu |
| Pseudocode | No | The paper describes algorithms but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Video, code and appendix can be found at https://sites.google. com/brown.edu/robustly-composing-options |
| Open Datasets | Yes | To answer these questions, we use a test-bed comprising four continuous-control maze-navigation tasks (shown in Figure 3) involving an ant robot simulated using Mu Jo Co [Todorov et al., 2012; Duan et al., 2016; Fu et al., 2020]. |
| Dataset Splits | No | The paper describes training and evaluation but does not specify explicit training/validation/test dataset splits with percentages, sample counts, or specific predefined split citations. |
| Hardware Specification | No | The paper mentions using 'computational resources and services at the Center for Computation and Visualization, Brown University' but does not provide specific hardware details such as GPU/CPU models, memory, or processor types. |
| Software Dependencies | No | The paper mentions software like TD3, HER, MuJoCo, and SVM, but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | After both algorithm variants were trained for 1000 episodes, they were evaluated on how many steps it would take them to reach the goal when starting in the four corners of the domain {( 9, 9)}. |