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.
Decoupling regularization from the action space
Authors: Sobhan Mohammadpour, Emma Frejinger, Pierre-Luc Bacon
ICLR 2024 | Venue PDF | LLM Run Details | Input Tokens: 17,015 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,790 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 this section, we provide three sets of experiments: a toy MDP where the number of actions is a parameter, a set of experiments on the Deep Mind Control suite (Tassa et al., 2018), and lastly, the drug design MDP of Bengio et al. (2021). |
| Researcher Affiliation | Academia | Anonymous authors Paper under double-blind review |
| Pseudocode | Yes | Algorithm 1 Decoupled SQL Algorithm 2 Soft actor-critic s update |
| Open Source Code | Yes | All code is hosted at https://anonymous.4open.science/r/decoupled_sql-5CAB/ and https://anonymous.4open.science/r/decoupled_gfn-8589. |
| Open Datasets | Yes | In this section, we provide three sets of experiments: a toy MDP where the number of actions is a parameter, a set of experiments on the Deep Mind Control suite (Tassa et al., 2018), and lastly, the drug design MDP of Bengio et al. (2021). |
| Dataset Splits | No | The paper does not explicitly state training/validation/test splits with percentages, counts, or specific citations for the datasets used. It refers to 'test rewards over the training' but lacks details on how the data was partitioned. |
| Hardware Specification | No | No specific hardware (e.g., GPU models, CPU models, memory details) used for running the experiments was mentioned in the paper. |
| Software Dependencies | No | No specific software dependencies with version numbers were mentioned in the paper. |
| Experiment Setup | Yes | In the first experiment, we fix the temperature to 0.25. We chose α 0.77 to get similar results as Haarnoja et al. (2018) when the actions are in the [ 1, 1] range, this is our recommended default. |