Recurrent Reinforcement Learning with Memoroids

arXiv:2402.09900 · cs.LG, cs.AI · Submitted 2024-02-15 · Read on arXiv

cs.LG, cs.AI

Submitted: 2024-02-15

Updated: 2026-08-27

Code: https://github.com/oogle/jax

Terminology

• Transformer — 22× in this paper · explained in 2 episodes
• Reinforcement Learning — 17× in this paper · explained in 4 episodes
• Loss Function — 11× in this paper · explained in 2 episodes
• Sample Efficiency — 9× in this paper · explained in 4 episodes
• Fast and Forgetful Memory — 7× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Generalized Advantage Estimate — 3× in this paper
• Tape-Based Batching — 3× in this paper
• Arcade Learning Environment — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Institutional Review Board — 2× in this paper
• Linear Recurrent Units — 2× in this paper
• Abstraction — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• In Segment-Based Batching — 1× in this paper
• Q-learning — 1× in this paper · explained in 3 episodes
• Real Time Recurrent Learning — 1× in this paper
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Memory Length — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes
• Value Memory Length — 1× in this paper
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Mastering Diverse Domains through World Models
• CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms
• Exploring the Promise and Limits of Real-Time Recurrent Learning
• RWKV: Reinventing RNNs for the Transformer Era
• Prioritized Experience Replay

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks