Partially Observable Environments - Groups

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially...
- Dataset
- JSON
DMLab-30

DMLab-30 is a benchmark for multitask reinforcement learning in partially observable environments.
- Dataset
- JSON

2 datasets found