Reachability-Aware Laplacian Representation in Reinforcement Learning
Authors: Kaixin Wang, Kuangqi Zhou, Jiashi Feng, Bryan Hooi, Xinchao Wang
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we conduct experiments to validate the benefits of RA-Lap Rep compared to Lap Rep. |
| Researcher Affiliation | Collaboration | 1Institute of Data Science, National University of Singapore, Singapore 2Department of Electrical and Computer Engineering, National University of Singapore, Singapore 3Byte Dance, Singapore 4School of Computing, National University of Singapore, Singapore. |
| Pseudocode | No | The paper describes methods in text and equations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide a direct link to a code repository or explicitly state that the source code for their method is publicly available. |
| Open Datasets | No | The paper uses environments built with Mini Grid (Chevalier-Boisvert et al., 2018) and Mu Jo Co (Todorov et al., 2012). It mentions collecting "a dataset of transitions" but does not provide access information (link, DOI, specific citation to a dataset resource) for this collected data. While the underlying frameworks are public, the specific datasets generated for their experiments are not explicitly made publicly available. |
| Dataset Splits | No | The paper does not explicitly specify train/validation/test dataset splits (e.g., percentages or absolute counts) for reproducibility. |
| Hardware Specification | Yes | Our experiments are run on Linux servers with Intel Core TM i7-5820K CPU and NVIDIA Titan X GPU. |
| Software Dependencies | No | The paper mentions optimizers and algorithms (e.g., Adam, DQN, DDPG) but does not provide specific version numbers for software dependencies or libraries (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | Table 1. Configurations for learning Lap Rep. Table 2. Configurations for reward shaping. (These tables list specific values for Dataset size, Episode length, Training iterations, Learning rate, Batch size, Lap Rep dimension d, Discount sampling, Timesteps, Optimizer, Learning starts, Target update rate, Replay size, Batch size, Discount factor γ, Action noise type, Gaussian noise σ.) |