REVIEW 11 cited by
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
read the original abstract
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.
Forward citations
Cited by 11 Pith papers
-
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
-
A Generalist Agent
Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.
-
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
Relabeling LLM-agent trajectories with all goals actually achieved, plus action masking and reweighting, yields sample-efficient gains over SFT and DPO on ALFWorld, PlanCraft, and WebShop.
-
Test-Time Deep Thinking to Explore Implicit Rules
TTExplore trains a 7B thinker via task-score RL to infer implicit rules at test time, raising agent success by 14-19 points on five embodied tasks.
-
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
WebFactory is a fully automated RL pipeline that compresses LLM-encoded internet knowledge into grounded web agents, achieving performance comparable to human-annotated training but using synthetic data from only 10 websites.
-
Dual-Process Atomic Skill Learning: Decoupling Semantic Reasoning and Real-Time Control
Asynchronous dual-frequency hierarchical imitation learning with VQ skills and training-only latent diffusion improves compositional language-conditioned robot control and reduces skill codebook collapse.
-
Analyzing Adversarial Inputs in Deep Reinforcement Learning
Introduces the Adversarial Rate metric and associated tools to systematically evaluate and visualize the impact of adversarial inputs on DRL policies using formal verification.
-
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.
-
Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
SuperIgor uses iterative co-training of a language model planner and a goal-conditional RL agent to self-generate and refine plans, resulting in stricter instruction adherence and better generalization to unseen instructions.
-
Why Build an Assistant in Minecraft?
A rationale is presented for developing an assistant in Minecraft to advance natural language understanding and dialogue learning.
-
Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback
Themis is an XAI-enabled framework for RL from human feedback that supports 200+ environments and includes a scalable cloud platform for collecting human preferences.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.