Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Constrained Intrinsic Motivation for Reinforcement Learning
Authors: Xiang Zheng, Xingjun Ma, Chao Shen, Cong Wang
IJCAI 2024 | Venue PDF | LLM Run Details | Input Tokens: 17,932 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,798 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In various Mu Jo Co robotics environments, we empirically show that CIM for RFPT greatly surpasses fifteen IM methods for unsupervised skill discovery in terms of skill diversity, state coverage, and fine-tuning performance. |
| Researcher Affiliation | Academia | Xiang Zheng1 , Xingjun Ma2 , Chao Shen3 and Cong Wang1 1City University of Hong Kong 2Fudan University 3Xi an Jiaotong University |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/x-zheng16/CIM. |
| Open Datasets | Yes | We evaluate our adaptive coefficient τ CIM k for EIM in two navigation tasks (Point Maze UMaze and Ant Maze UMaze) in D4RL [Fu et al., 2020], and four sparse-reward tasks (Sparse Half Cheetah, Sparse Ant, Sparse Humanoid Standup, and Sparse Grid World). |
| Dataset Splits | No | The paper does not provide specific dataset split information for validation. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment. |
| Experiment Setup | Yes | 4.1 Experimental Setup. We evaluate our intrinsic bonus r CIM I for RFPT tasks on four Gymnasium environments, including two locomotion environments (Ant and Humanoid) and two manipulation environments (Fetch Push and Fetch Slide). |