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.
Same State, Different Task: Continual Reinforcement Learning without Interference
Authors: Samuel Kessler, Jack Parker-Holder, Philip Ball, Stefan Zohren, Stephen J. Roberts7143-7151
AAAI 2022 | Venue PDF | LLM Run Details | Input Tokens: 18,020 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,030 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 show in multiple RL environments that existing replay based CL methods fail, while OWL is able to achieve close to optimal performance when training sequentially. |
| Researcher Affiliation | Academia | University of Oxford EMAIL |
| Pseudocode | Yes | Algorithm 1: OWL: Training |
| Open Source Code | Yes | Code is available at https://github.com/skezle/owl. |
| Open Datasets | Yes | Pendulum-v0 environment (Brockman et al. 2016) |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions some general training durations (e.g., 'switching every 20, 000 environment steps', '1M steps') but does not provide specific experimental setup details such as concrete hyperparameter values or optimizer settings in the main text. |