Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for efficient multi-task reinforcement learning. Our framework trains agents to employ hierarchical policies that decide when to use a previously learned policy and when to learn a new skill. This enables agents to continually acquire new skills during different stages of training. Each learned task corresponds to a human language description. Because agents can only access previously learned skills through these descriptions, the agent can always provide a human-interpretable description of its choices. In order to help the agent learn the complex temporal dependencies necessary for the hierarchical policy, we provide it with a stochastic temporal grammar that modulates when to rely on previously learned skills and when to execute new skills. We validate our approach on Minecraft games designed to explicitly test the ability to reuse previously learned skills while simultaneously learning new skills.
fields
cs.AI 3representative citing papers
CraftAssist supplies a Minecraft bot, dialogue interface, and data-recording platform intended to support research on agents that execute tasks specified through conversation.
A rationale is presented for developing an assistant in Minecraft to advance natural language understanding and dialogue learning.
citing papers explorer
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
CraftAssist: A Framework for Dialogue-enabled Interactive Agents
CraftAssist supplies a Minecraft bot, dialogue interface, and data-recording platform intended to support research on agents that execute tasks specified through conversation.
-
Why Build an Assistant in Minecraft?
A rationale is presented for developing an assistant in Minecraft to advance natural language understanding and dialogue learning.