Lipschitz Lifelong Reinforcement Learning
Authors: Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman8270-8278
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We illustrate the benefits of the method in Lifelong RL experiments. ... We illustrate the benefits of the method in Lifelong RL experiments. ... Section 5: Experiments |
| Researcher Affiliation | Collaboration | 1ISAE-SUPAERO, Universit e de Toulouse, France 2ONERA, The French Aerospace Lab, Toulouse, France 3Brown University, Providence, Rhode Island, USA 4Amazon Web Service, Palo Alto, California, USA |
| Pseudocode | Yes | Algorithm 1: Lipschitz RMax algorithm |
| Open Source Code | Yes | Code available at https://github.com/Su Re LI/llrl |
| Open Datasets | Yes | The environment used in all experiments is a variant of the tight task used by Abel et al. (2018). |
| Dataset Splits | No | The paper describes the experimental setup in an RL context, including sampling tasks sequentially and running episodes. It does not provide explicit training/validation/test dataset splits as typically found in supervised learning, nor does it specify cross-validation folds. It mentions repeating operations '10 times to narrow the confidence intervals' which refers to overall experimental runs rather than dataset splitting. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as CPU or GPU models, memory specifications, or cloud computing instance types. |
| Software Dependencies | No | The paper does not list specific software dependencies or libraries with their version numbers (e.g., Python 3.8, PyTorch 1.9, TensorFlow 2.x) that are required to reproduce the experiments. |
| Experiment Setup | Yes | We set nknown = 10, δ = 0.05, and ϵ = 0.01 (discussion in Appendix, Section 15). ... We sample 15 tasks sequentially among this set, each run for 2000 episodes of length 10. |