Канал: UoE Agents Group

Riccardo Zamboni - Pure Exploration in POMDP: limits and possible solutions

Riccardo Zamboni - Pure Exploration in POMDP: limits and possible solutions

Jianxiong Li and Jinliang Zheng - Towards generalizable and sample-efficient Embodied AI

Jianxiong Li and Jinliang Zheng - Towards generalizable and sample-efficient Embodied AI

Davide Paglieri - Adversarial examples to Multi-Agent RL with Quality Diversity

Davide Paglieri - Adversarial examples to Multi-Agent RL with Quality Diversity

Eduardo Pignatelli - On the temporal credit assignment in Deep RL

Eduardo Pignatelli - On the temporal credit assignment in Deep RL

Yifan Zhong & Jiarong Liu - Maximum Entropy Heterogeneous-Agent Reinforcement Learning

Yifan Zhong & Jiarong Liu - Maximum Entropy Heterogeneous-Agent Reinforcement Learning

From Deep Reinforcement Learning to LLM-based Agents: Perspectives on Current Research

From Deep Reinforcement Learning to LLM-based Agents: Perspectives on Current Research

Joe Marino - Modern Video Games as a Testbed for Developing Generalist AI Agents

Joe Marino - Modern Video Games as a Testbed for Developing Generalist AI Agents

David Abel - A Definition of Continual Reinforcement Learning

David Abel - A Definition of Continual Reinforcement Learning

Pablo Samuel Castro - Mixtures of Experts Unlock Parameter Scaling for Deep RL

Pablo Samuel Castro - Mixtures of Experts Unlock Parameter Scaling for Deep RL

Matthias Gerstgrasser - Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

Matthias Gerstgrasser - Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

Geraud Tasse - Generalisation in Lifelong Reinforcement Learning through Logical Composition

Geraud Tasse - Generalisation in Lifelong Reinforcement Learning through Logical Composition

Nicholas Corrado - On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling

Nicholas Corrado - On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling

Mhairi Dunion - Temporal Disentanglement of Representations for Improved Generalisation in RL

Mhairi Dunion - Temporal Disentanglement of Representations for Improved Generalisation in RL

James Ault - MARL for multi-intersection signal control

James Ault - MARL for multi-intersection signal control

Lukas Schäfer - Ensemble Value Functions for Efficient Exploration in Multi-Agent RL

Lukas Schäfer - Ensemble Value Functions for Efficient Exploration in Multi-Agent RL

Chentian Jiang - Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

Chentian Jiang - Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

Thomas Burns - Detecting danger in gridworlds using Gromov's Link Condition

Thomas Burns - Detecting danger in gridworlds using Gromov's Link Condition

Charline Le Lan - On the Generalization of Representations in Reinforcement Learning

Charline Le Lan - On the Generalization of Representations in Reinforcement Learning

Jason Ma - How Far I'll Go: Offline Goal-Conditioned RL via f-Advantage Regression

Jason Ma - How Far I'll Go: Offline Goal-Conditioned RL via f-Advantage Regression

Jack Parker-Holder & Minqi Jiang - Open-Ended Learning Leads to Generally Capable Agents

Jack Parker-Holder & Minqi Jiang - Open-Ended Learning Leads to Generally Capable Agents

Pablo Samuel Castro - MICo: Improved representations via sampling-based state similarity for MDPs

Pablo Samuel Castro - MICo: Improved representations via sampling-based state similarity for MDPs

Rishabh Agarwal - Deep reinforcement learning at the edge of the statistical precipice

Rishabh Agarwal - Deep reinforcement learning at the edge of the statistical precipice

Mohamad H. Danesh - Re-understanding finite-state representations of recurrent policy networks

Mohamad H. Danesh - Re-understanding finite-state representations of recurrent policy networks

Andrei Lupu - Reinforcement learning with prototypical representations

Andrei Lupu - Reinforcement learning with prototypical representations

Jacopo Castellini - Difference Rewards Policy Gradients

Jacopo Castellini - Difference Rewards Policy Gradients