The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

Permutation-Invariant Neural Networks for Reinforcement Learning

--> This page requires Javascript. Please enable it for https://attentionagent.github.io/ Examples of permutation-invariant reinforcement learning agents In this work, we investigate the properties of RL agents that treat their observations as an arbitrarily ordered, variable-length list of sensory inputs. Here, we partition the visual input from CarRacing (Left) and Atari Pong (right) into a 2D grid of small patches, and shuffled their ordering. Each sensory neuron in the system receives a stream of visual input at a particular permuted patch location, and through coordination, must complete

related reading

• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• [1810.00825] Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networksarxiv.org
• The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
• Set Transformer: A Framework for Attention-basedPermutation-Invariant Neural Networksarxiv.org
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• Learning Beyond Gradientstrinkle23897.github.io
• Ch. 21 - Imitation Learningunderactuated.mit.edu
• Reinforcement learning with imperceptible rewards — AI Alignment Forumalignmentforum.org
• ERCEIVER-ACTOR: A Multi-Task Transformer for Robotic Manipulationarxiv.org
• Transformers from scratch | peterbloem.nlpeterbloem.nl
• Deep Reinforcement Learning: Pong from Pixelskarpathy.github.io
• 2106.01345arxiv.org