Learning Multi-Object Positional Relationships via Emergent Communication
Authors: Yicheng Feng, Boshi An, Zongqing Lu
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We train agents in the referential game where observations contain two objects, and find that generalization is the major problem when the positional relationship is involved. The key factor affecting the generalization ability of the emergent language is the input variation between Speaker and Listener, which is realized by a random image generator in our work. Further, we find that the learned language can generalize well in a new multi-step MDP task where the positional relationship describes the goal, and performs better than raw-pixel images as well as pre-trained image features, verifying the strong generalization ability of discrete sequences. |
| Researcher Affiliation | Academia | Yicheng Feng*, Boshi An*, Zongqing Lu School of Computer Science, Peking University {fyc813@, boshi.an@stu., zongqing.lu@}pku.edu.cn |
| Pseudocode | No | The paper describes the agent architecture and experimental procedures in narrative text without providing structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or a link indicating that the source code for the methodology is openly available. |
| Open Datasets | No | We create a dataset where we generate images of size 128 128 each depicting two objects with a certain positional relationship between them. |
| Dataset Splits | No | The paper mentions separating combinations into a test set and candidate images for training and test, but does not explicitly define a separate validation dataset split. |
| Hardware Specification | No | The paper does not specify the hardware (e.g., CPU, GPU models, or cloud instances) used for running the experiments. |
| Software Dependencies | No | The paper mentions algorithms and optimizers used (e.g., REINFORCE, Adam optimizer, PPO, LSTM), but does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | We set the message length T = 6, the size of vocabulary |V| = 5, and the number of candidate images |C| = 32 for training and |C| = 20 for test in the referential game... We use the default Adam optimizer (Kingma and Ba 2015) with a learning rate of 3e-5 to update the parameters. |