2406.00392

N/A

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning Jonathan Cook ∗ Chris Lu ∗ FLAIR, University of Oxford FLAIR, University of Oxford jonathan.cook2@hertford.ox.ac.uk christopher.lu@eng.ox.ac.uk arXiv:2406.00392v2 [cs.AI] 28 Oct 2024…

saved by

• Micah Carroll

related reading

• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• [2606.12016] Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalizationarxiv.org
• Quantifying Generalization in Reinforcement Learningarxiv.org
• pdfopenreview.net
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• [2602.05999] On the Role of Computation in Reinforcement Learningarxiv.org
• [1606.05312] Successor Features for Transfer in Reinforcement Learningarxiv.org
• [2606.05555] Representation Learning Enables Scalable Multitask Deep Reinforcement Learningarxiv.org
• Learning Beyond Gradientstrinkle23897.github.io
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org