Foundational challenges in assuring alignment and safety of large language models
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …
language models (LLMs). These challenges are organized into three different categories …
Motif: Intrinsic motivation from artificial intelligence feedback
Exploring rich environments and evaluating one's actions without prior knowledge is
immensely challenging. In this paper, we propose Motif, a general method to interface such …
immensely challenging. In this paper, we propose Motif, a general method to interface such …
diff History for Long-Context Language Agents
Language Models (LMs) offer an exciting solution for general-purpose embodied control.
However, a key technical issue arises when using an LM-based controller: environment …
However, a key technical issue arises when using an LM-based controller: environment …
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained
capabilities, as recently showcased by the successful applications of foundation models …
capabilities, as recently showcased by the successful applications of foundation models …
Syllabus: Portable Curricula for Reinforcement Learning Agents
R Sullivan, R Pégoud, AU Rahmen, X Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
Curriculum learning has been a quiet yet crucial component of many of the high-profile
successes of reinforcement learning. Despite this, none of the major reinforcement learning …
successes of reinforcement learning. Despite this, none of the major reinforcement learning …
AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
O Neumann, C Gros - arXiv preprint arXiv:2412.11979, 2024 - arxiv.org
Neural scaling laws are observed in a range of domains, to date with no clear understanding
of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a …
of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a …
diff History for Neural Language Agents
Neural Language Models (LMs) offer an exciting solution for general-purpose embodied
control. However, a key technical issue arises when using an LM-based controller …
control. However, a key technical issue arises when using an LM-based controller …
[PDF][PDF] Enhancing PPO with Intrinsic Rewards: A Study in the NetHack Environment
P Yanushonak - 2024 - dspace.cuni.cz
This thesis evaluates the effectiveness of various intrinsic reward mechanisms in enhancing
the performance of Asynchronous Proximal Policy Optimization (APPO) in a complex, sparse …
the performance of Asynchronous Proximal Policy Optimization (APPO) in a complex, sparse …