UoE Agents Group
182 subscribers
34:24
Daphne Cornelisse - Human-compatible driving partners through data-regularized self-play RL
UoE Agents Group
3 views • 2 hours ago
56:58
Riccardo Zamboni - Pure Exploration in POMDP: limits and possible solutions
UoE Agents Group
45 views • 1 month ago
1:04:07
Jianxiong Li and Jinliang Zheng - Towards generalizable and sample-efficient Embodied AI
UoE Agents Group
59 views • 1 month ago
37:06
Davide Paglieri - Adversarial examples to Multi-Agent RL with Quality Diversity
UoE Agents Group
61 views • 1 month ago
1:16:46
Eduardo Pignatelli - On the temporal credit assignment in Deep RL
UoE Agents Group
33 views • 1 month ago
42:26
Yifan Zhong & Jiarong Liu - Maximum Entropy Heterogeneous-Agent Reinforcement Learning
UoE Agents Group
75 views • 1 month ago
43:46
From Deep Reinforcement Learning to LLM-based Agents: Perspectives on Current Research
UoE Agents Group
601 views • 3 months ago
57:48
Joe Marino - Modern Video Games as a Testbed for Developing Generalist AI Agents
UoE Agents Group
105 views • 3 months ago
53:00
David Abel - A Definition of Continual Reinforcement Learning
UoE Agents Group
230 views • 4 months ago
51:27
Pablo Samuel Castro - Mixtures of Experts Unlock Parameter Scaling for Deep RL
UoE Agents Group
164 views • 4 months ago
31:21
Matthias Gerstgrasser - Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
UoE Agents Group
32 views • 4 months ago
55:35
Geraud Tasse - Generalisation in Lifelong Reinforcement Learning through Logical Composition
UoE Agents Group
34 views • 4 months ago
51:53
Nicholas Corrado - On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
UoE Agents Group
13 views • 4 months ago
13:29
Mhairi Dunion - Temporal Disentanglement of Representations for Improved Generalisation in RL
UoE Agents Group
25 views • 4 months ago
41:16
James Ault - MARL for multi-intersection signal control
UoE Agents Group
6 views • 4 months ago
39:45
Lukas Schäfer - Ensemble Value Functions for Efficient Exploration in Multi-Agent RL
UoE Agents Group
37 views • 4 months ago
46:32
Chentian Jiang - Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
UoE Agents Group
3 views • 4 months ago
48:03
Thomas Burns - Detecting danger in gridworlds using Gromov's Link Condition
UoE Agents Group
11 views • 4 months ago
42:50
Charline Le Lan - On the Generalization of Representations in Reinforcement Learning
UoE Agents Group
27 views • 4 months ago
47:34
Jason Ma - How Far I'll Go: Offline Goal-Conditioned RL via f-Advantage Regression
UoE Agents Group
15 views • 4 months ago
26:26
Jack Parker-Holder & Minqi Jiang - Open-Ended Learning Leads to Generally Capable Agents
UoE Agents Group
4 views • 4 months ago
32:31
Pablo Samuel Castro - MICo: Improved representations via sampling-based state similarity for MDPs
UoE Agents Group
42 views • 4 months ago
37:20
Rishabh Agarwal - Deep reinforcement learning at the edge of the statistical precipice
UoE Agents Group
20 views • 4 months ago
28:19
Mohamad H. Danesh - Re-understanding finite-state representations of recurrent policy networks
UoE Agents Group
4 views • 4 months ago
39:11
Andrei Lupu - Reinforcement learning with prototypical representations
UoE Agents Group
7 views • 4 months ago
35:29
Jacopo Castellini - Difference Rewards Policy Gradients
UoE Agents Group
8 views • 4 months ago
End of Videos