English
Related papers

Related papers: Automating Curriculum Learning for Reinforcement L…

200 papers

Curriculum learning allows complex tasks to be mastered via incremental progression over `stepping stone' goals towards a final desired behaviour. Typical implementations learn locomotion policies for challenging environments through…

Neural and Evolutionary Computing · Computer Science 2022-03-30 David Howard , Josh Kannemeyer , Davide Dolcetti , Humphrey Munn , Nicole Robinson

It is common knowledge that the quantity and quality of the training data play a significant role in the creation of a good machine learning model. In this paper, we take it one step further and demonstrate that the way the training…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-12 Georgios Karakasidis , Tamás Grósz , Mikko Kurimo

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased…

Machine Learning · Computer Science 2020-07-28 Karl Cobbe , Christopher Hesse , Jacob Hilton , John Schulman

A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task. Different types of representations may be suited to different types of tasks,…

Machine Learning · Computer Science 2023-07-18 Ryan Pyle , Sebastian Musslick , Jonathan D. Cohen , Ankit B. Patel

We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which…

Artificial Intelligence · Computer Science 2026-01-08 Haochen Shi , Xingdi Yuan , Bang Liu

The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms…

Machine Learning · Computer Science 2020-10-16 Geraud Nangue Tasse , Steven James , Benjamin Rosman

This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected…

Artificial Intelligence · Computer Science 2015-05-18 Zhipeng Wang , Mingbo Cai

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

In this paper the problem of learning appropriate bias for an environment of related tasks is examined from a Bayesian perspective. The environment of related tasks is shown to be naturally modelled by the concept of an {\em objective}…

Machine Learning · Computer Science 2019-11-15 Jonathan Baxter

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the…

Machine Learning · Computer Science 2015-09-24 Samy Bengio , Oriol Vinyals , Navdeep Jaitly , Noam Shazeer

We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning. This is accomplished by a probabilistic model-based approach…

A wide range of machine learning algorithms iteratively add data to the training sample. Examples include semi-supervised learning, active learning, multi-armed bandits, and Bayesian optimization. We embed this kind of data addition into…

Machine Learning · Statistics 2024-06-25 Julian Rodemann

A representation of the cause-effect mechanism is needed to enable artificial intelligence to represent how the world works. Bayesian Networks (BNs) have proven to be an effective and versatile tool for this task. BNs require constructing a…

Artificial Intelligence · Computer Science 2026-03-18 Joverlyn Gaudillo , Nicole Astrologo , Fabio Stella , Enzo Acerbi , Francesco Canonaco

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Robotics · Computer Science 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as…

Machine Learning · Computer Science 2020-06-24 Tatsuya Matsushima , Hiroki Furuta , Yutaka Matsuo , Ofir Nachum , Shixiang Gu

Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typically require domain-specific hyperparameter tuning, involve…

Machine Learning · Computer Science 2024-05-07 Georgios Tzannetos , Parameswaran Kamalaruban , Adish Singla

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum…

Machine Learning · Computer Science 2021-07-28 Vinu Sankar Sadasivan , Anirban Dasgupta

This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based…

Machine Learning · Computer Science 2020-07-09 Andrey Gorodetskiy , Alexandra Shlychkova , Aleksandr I. Panov

We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We provide a unified…

Machine Learning · Computer Science 2021-12-17 Gaurav Yengera , Rati Devidze , Parameswaran Kamalaruban , Adish Singla

Bayesian neural Networks (BNNs) are a promising method of obtaining statistical uncertainties for neural network predictions but with a higher computational overhead which can limit their practical usage. This work explores the use of high…

Machine Learning · Computer Science 2020-09-09 Himanshu Sharma , Elise Jennings