Zobrazeno 1 - 10
of 21
pro vyhledávání: '"McInroe, Trevor A."'
Recent work has demonstrated both benefits and limitations from using supervised approaches (without temporal-difference learning) for offline reinforcement learning. While off-policy reinforcement learning provides a promising approach for improving
Externí odkaz:
http://arxiv.org/abs/2406.13376
Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a c
Externí odkaz:
http://arxiv.org/abs/2404.14285
Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process. In this scenario, we aim to find the best-performing policy within a limited budget
Externí odkaz:
http://arxiv.org/abs/2310.05723
Autor:
Dunion, Mhairi, McInroe, Trevor, Luck, Kevin Sebastian, Hanna, Josiah P., Albrecht, Stefano V.
Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading correlations in th
Externí odkaz:
http://arxiv.org/abs/2305.14133
Autor:
Ahmed, Ibrahim H., Brewitt, Cillian, Carlucho, Ignacio, Christianos, Filippos, Dunion, Mhairi, Fosong, Elliot, Garcin, Samuel, Guo, Shangmin, Gyevnar, Balint, McInroe, Trevor, Papoudakis, Georgios, Rahman, Arrasy, Schäfer, Lukas, Tamborski, Massimiliano, Vecchio, Giuseppe, Wang, Cheng, Albrecht, Stefano V.
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel ma
Externí odkaz:
http://arxiv.org/abs/2208.01769
Autor:
Dunion, Mhairi, McInroe, Trevor, Luck, Kevin Sebastian, Hanna, Josiah P., Albrecht, Stefano V.
Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training. This issue is especially problematic for image-based RL, where a change in just one variable,
Externí odkaz:
http://arxiv.org/abs/2207.05480
Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either
Externí odkaz:
http://arxiv.org/abs/2206.11396
Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which requires
Externí odkaz:
http://arxiv.org/abs/2110.04935
We analyze the hidden activations of neural network policies of deep reinforcement learning (RL) agents and show, empirically, that it's possible to know a priori if a state representation will lend itself to fast learning. RL agents in high-dimensio
Externí odkaz:
http://arxiv.org/abs/2103.06398
Autor:
McInroe, Trevor A.
Sparse rewards present a difficult problem in reinforcement learning and may be inevitable in certain domains with complex dynamics such as real-world robotics. Hindsight Experience Replay (HER) is a recent replay memory development that allows agent
Externí odkaz:
http://arxiv.org/abs/2008.12693