Adaptive Rational Activations to Boost Deep Reinforcement Learning
Quentin Delfosse, Patrick Schramowski, Martin Mundt, Alejandro Molina, Kristian Kersting
Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility than previously anticipated. This perspective should be critical in the context of constantly changing distinct reinforcement learning environments, yet current approaches still primarily employ static activation functions. In this work, we mo ...
tivate why rationals are suitable for adaptable activation functions and why their inclusion into neural networks is crucial. Inspired by recurrence in residual networks, we derive a condition under which rational units are closed under residual connections and formulate a naturally regularised version: the recurrent-rational. We demonstrate that equipping popular algorithms with (recurrent-)rational activations leads to consistent improvements on Atari games, especially turning simple DQN into a solid approach, competitive to DDQN and Rainbow.
Results & Benchmarks
No concrete benchmark grounding is available yet. Treat the page as context or an implementation starting point only.
Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility than previously anticipated.
Implementation Evidence Summary
Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.
Reproduction Risks
- Estimate is based on paper-only reproduction flow
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence disclosure
Evidence graph: 2 refs, 1 links.
Utility signals: depth 65/100, grounding 58/100, status medium.
Implementation Status
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.
- Start from related paper: New Characterizations of Simple Points, Minimal Non-simple Sets and P-Simple Points in 2D, 3D and 4D Discrete Spaces.
- Start from this likely method family: Reinforcement learning.
Reproduction readiness
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
No verified implementation available
- · No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
No benchmark numbers could be verified. You will not be able to validate reproduction correctness against published numbers.
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet.
Continue with targeted Hugging Face searches derived from the paper title and method context:
Datasets
Tip: start with models, then check datasets/spaces if you need evaluation data or demos.
Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.
Research context
2
Citations
0
References
Tasks
Computer science, Context (archaeology), Perspective (graphical), Simple (philosophy), Residual, Cognitive science, Physical Sciences
Methods
Reinforcement learning
Domains
Artificial intelligence
Evaluation & Human Feedback Data
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXExplore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Related papers
-
Search on Paper2Code
New Characterizations of Simple Points, Minimal Non-simple Sets and P-Simple Points in 2D, 3D and 4D Discrete Spaces (2008) Semantic similarity
-
Search on Paper2Code
The [0-Simple] Simple Subsemigroups of Nonnegative Matrices (2000) Semantic similarity
-
Search on Paper2Code
Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Market Environment (2022) Semantic similarity
-
Search on Paper2Code
Fundamental relations in simple and 0-simple semihypergroups of small size (2012) Semantic similarity
-
Search on Paper2Code
Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks (2016) Semantic similarity
-
Search on Paper2Code
Which side are you on? (2006) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.