Learning as Reinforcement: Applying Principles of Neuroscience for More General Reinforcement Learning Agents

2020-04-20 · Eric Zelikman, William Yin, Kenneth Wang

A significant challenge in developing AI that can generalize well is designing agents that learn about their world without being told what to learn, and apply that learning to challenges with sparse rewards. Moreover, most traditional reinforcement learning approaches explicitly separate learning and decision making in a way that does not correspond to biological learning. We implement an architecture founded in principles of experimental neuroscience, by combining computationally efficient abstractions of biological algorithms. Our approach is inspired by research on spike-timing dependent plasticity, the transition between short and long term memory, and the role of various neurotransmitters in rewarding curiosity. The Neurons-in-a-Box architecture can learn in a wholly generalizable manner, and demonstrates an efficient way to build and apply representations without explicitly optimizing over a set of criteria or actions. We find it performs well in many environments including OpenAI Gym's Mountain Car, which has no reward besides touching a hard-to-reach flag on a hill, Inverted Pendulum, where it learns simple strategies to improve the time it holds a pendulum up, a video stream, where it spontaneously learns to distinguish an open and closed hand, as well as other environments like Google Chrome's Dinosaur Game.

📄 PDF Abstract BibTeX arXiv:2004.09043

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making General Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep reinforcement learning with time-scale invariant memory

2024-12-19 · Md Rysul Kabir, James Mochizuki-Freeman, Zoran Tiganj

The ability to estimate temporal relationships is critical for both animals and artificial agents. Cognitive science and neuroscience provide remarkable insights into behavioral and neural aspects of temporal credit assi…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Brain as a complex system, harnessing systems neuroscience tools & notions for an empirical approach

2023-12-20 · Shervin Safavi

Finding general principles underlying brain function has been appealing to scientists. Indeed, in some branches of science like physics and chemistry (and to some degree biology) a general theory often can capture the es…

Context sequence theory: a common explanation for multiple types of learning

2022-07-17 · Yu Mingcan, Wang Junying

Although principles of neuroscience like reinforcement learning, visual perception and attention have been applied in machine learning models, there is a huge gap between machine learning and mammalian learning. Based on…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A perspective on neuroscience data standardization with Neurodata Without Borders

2023-10-06 · Andrea Pierré, Tuan Pham, Jonah Pearl, Sandeep Robert Datta 외

Neuroscience research has evolved to generate increasingly large and complex experimental data sets, and advanced data science tools are taking on central roles in neuroscience research. Neurodata Without Borders (NWB), …

Management

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics

2019-08-13 · NeurIPS 2020 12 · Saurabh Daptardar, Paul Schrater, Xaq Pitkow

Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is uncle…

continuous-control Continuous Control