paper-with-me

홈 › Papers

The MineRL BASALT Competition on Learning from Human Feedback

2021-07-05 · Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William Guss, Sharada Mohanty, Anssi Kanervisto, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca Dragan

The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are now being incorporated into commercial products. With this comes an additional challenge: how can we build AI systems that solve tasks where there is not a crisp, well-defined specification? While multiple solutions have been proposed, in this competition we focus on one in particular: learning from human feedback. Rather than training AI systems using a predefined reward function or using a labeled dataset with a predefined set of categories, we instead train the AI system using a learning signal derived from some form of human feedback, which can evolve over time as the understanding of the task changes, or as the capabilities of the AI system improve. The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. These tasks are defined by a paragraph of natural language: for example, "create a waterfall and take a scenic picture of it", with additional clarifying details. Participants must train a separate agent for each task, using any method they want. Agents are then evaluated by humans who have read the task description. To help participants get started, we provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline that leverages these demonstrations. Our hope is that this competition will improve our ability to build AI systems that do what their designers intend them to do, even when the intent cannot be easily formalized. Besides allowing AI to solve more tasks, this can also enable more effective regulation of AI systems, as well as making progress on the value alignment problem.

📄 PDF Abstract BibTeX arXiv:2107.01969

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningMinecraft

Similar Papers 제목 키워드 기반

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

2023-03-23 · Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff 외

To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to c…

Minecraft

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

2023-12-05 · NeurIPS 2023 11 · Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff 외

The MineRL BASALT competition has served to catalyze advances in learning from human feedback through four hard-to-specify tasks in Minecraft, such as create and photograph a waterfall. Given the completion of two years …

BenchmarkingMinecraft

Retrospective on the 2021 BASALT Competition on Learning from Human Feedback

2022-04-14 · Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani 외

We held the first-ever MineRL Benchmark for Agents that Solve Almost-Lifelike Tasks (MineRL BASALT) Competition at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021). The goal of the comp…

Minecraft

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft

2021-12-07 · Vinicius G. Goecks, Nicholas Waytowich, David Watkins-Valls, Bharat Prakash

Real-world tasks of interest are generally poorly defined by human-readable descriptions and have no pre-defined reward signals unless it is defined by a human designer. Conversely, data-driven algorithms are often desig…

Imitation LearningMinecraft

DIP-RL: Demonstration-Inferred Preference Learning in Minecraft

2023-07-22 · Ellen Novoseller, Vinicius G. Goecks, David Watkins, Josh Miller 외

In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal. However, in many unstructured real-world settings, …

Decision MakingMinecraftreinforcement-learningReinforcement Learning+2