Search Results for author:
Found 14 papers, 9 papers with code
Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
Tokenization, the division of input text into input tokens, is an often overlooked aspect of the large language model (LLM) pipeline and could be the source of useful or harmful inductive biases.
Confronting Reward Model Overoptimization with Constrained RLHF
Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback.
Melting Pot 2.0
Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios.
In-context Reinforcement Learning with Algorithm Distillation
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model.
Semantic Exploration from Language Abstractions and Pretrained Representations
We show that these pretrained representations drive meaningful, task-relevant exploration and improve performance on 3D simulated environments.
Collaborating with Humans without Human Data
Here, we study the problem of how to train agents that collaborate well with human partners without using human data.
Learning more skills through optimistic exploration
However, an inherent exploration problem lingers: when a novel state is actually encountered, the discriminator will necessarily not have seen enough training data to produce accurate and confident skill classifications, leading to low intrinsic reward for the agent and effective penalization of the sort of exploration needed to actually maximize the objective.
Learning Truthful, Efficient, and Welfare Maximizing Auction Rules
From social networks to supply chains, more and more aspects of how humans, firms and organizations interact is mediated by artificial learning agents.
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward.
Transfer and Exploration via the Information Bottleneck
In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
Learning to Share and Hide Intentions using Information Regularization
We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
The information bottleneck and geometric clustering
The information bottleneck (IB) approach to clustering takes a joint distribution $P\!\left(X, Y\right)$ and maps the data $X$ to cluster labels $T$ which retain maximal information about $Y$ (Tishby et al., 1999).
The deterministic information bottleneck
Here, we introduce an alternative formulation that replaces mutual information with entropy, which we call the deterministic information bottleneck (DIB), that we argue better captures this notion of compression.
