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.
Learning to Share and Hide Intentions using Information Regularization
Authors: DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matt Botvinick, David J. Schwab
NeurIPS 2018 | Venue PDF | LLM Run Details | Input Tokens: 16,096 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,188 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 | We demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games. |
| Researcher Affiliation | Collaboration | 1 Princeton University, 2 MIT, 3 Deep Mind 4 UCL, 5 CUNY Graduate Center |
| Pseudocode | Yes | Algorithm 1 Action information regularized REINFORCE with value baseline. ... Algorithm 2 State information regularized REINFORCE with value baseline. |
| Open Source Code | Yes | Our code is available at https://github.com/djstrouse/Info MARL. |
| Open Datasets | No | The paper describes custom simulated environments (a 5x5 grid world and a key-and-door game) but does not provide concrete access information for a publicly available or open dataset used for training. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology). |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions 'Tensor Flow [Abadi et al., 2016]' but does not provide specific version numbers for TensorFlow or any other software dependencies. |
| Experiment Setup | Yes | Alice was trained using implementations of algorithms 2.1 and 2.2 in Tensor Flow [Abadi et al., 2016]. Given the small, discrete environment, we used tabular representations for both π and V . See section S2.1 for training parameters. ... (see section S2.2 for training parameters). |