Task-Oriented Language Grounding for Language Input with Multiple Sub-Goals of Non-Linear Order
This addresses language understanding for AI agents in sequential tasks, but it is incremental as it builds on existing deep reinforcement learning methods with minor modifications.
The paper tackled the problem of task-oriented language grounding with multiple sub-goals in non-linear order, finding that introducing non-linear order connectors improved success rates by 2-3 times for instructions with more sub-goals, though rates remained below 20%.
In this work, we analyze the performance of general deep reinforcement learning algorithms for a task-oriented language grounding problem, where language input contains multiple sub-goals and their order of execution is non-linear. We generate a simple instructional language for the GridWorld environment, that is built around three language elements (order connectors) defining the order of execution: one linear - "comma" and two non-linear - "but first", "but before". We apply one of the deep reinforcement learning baselines - Double DQN with frame stacking and ablate several extensions such as Prioritized Experience Replay and Gated-Attention architecture. Our results show that the introduction of non-linear order connectors improves the success rate on instructions with a higher number of sub-goals in 2-3 times, but it still does not exceed 20%. Also, we observe that the usage of Gated-Attention provides no competitive advantage against concatenation in this setting. Source code and experiments' results are available at https://github.com/vkurenkov/language-grounding-multigoal