Zobrazeno 1 - 10
of 303
pro vyhledávání: '"Byravan A"'
We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency and transfer learning in reinforcement learning for embodied agents. DAA
Externí odkaz:
http://arxiv.org/abs/2407.20798
Autor:
Tirumala, Dhruva, Wulfmeier, Markus, Moran, Ben, Huang, Sandy, Humplik, Jan, Lever, Guy, Haarnoja, Tuomas, Hasenclever, Leonard, Byravan, Arunkumar, Batchelor, Nathan, Sreendra, Neil, Patel, Kushal, Gwira, Marlon, Nori, Francesco, Riedmiller, Martin, Heess, Nicolas
We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perce
Externí odkaz:
http://arxiv.org/abs/2405.02425
Autor:
Bhardwaj, Mohak, Lampe, Thomas, Neunert, Michael, Romano, Francesco, Abdolmaleki, Abbas, Byravan, Arunkumar, Wulfmeier, Markus, Riedmiller, Martin, Buchli, Jonas
Recent advances in real-world applications of reinforcement learning (RL) have relied on the ability to accurately simulate systems at scale. However, domains such as fluid dynamical systems exhibit complex dynamic phenomena that are hard to simulate
Externí odkaz:
http://arxiv.org/abs/2402.06102
Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments into computing infrastructure. Although earlier successes predominantly f
Externí odkaz:
http://arxiv.org/abs/2312.01939
Autor:
Pinneri, Cristina, Bechtle, Sarah, Wulfmeier, Markus, Byravan, Arunkumar, Zhang, Jingwei, Whitney, William F., Riedmiller, Martin
We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment. Specifically, we aim to improve the ag
Externí odkaz:
http://arxiv.org/abs/2309.07578
Autor:
Di Palo, Norman, Byravan, Arunkumar, Hasenclever, Leonard, Wulfmeier, Markus, Heess, Nicolas, Riedmiller, Martin
Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, w
Externí odkaz:
http://arxiv.org/abs/2307.09668
Autor:
Schubert, Ingmar, Zhang, Jingwei, Bruce, Jake, Bechtle, Sarah, Parisotto, Emilio, Riedmiller, Martin, Springenberg, Jost Tobias, Byravan, Arunkumar, Hasenclever, Leonard, Heess, Nicolas
We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, both in a few-shot setting, where a generalist TDM is fine-tuned with sm
Externí odkaz:
http://arxiv.org/abs/2305.10912
Autor:
Haarnoja, Tuomas, Moran, Ben, Lever, Guy, Huang, Sandy H., Tirumala, Dhruva, Humplik, Jan, Wulfmeier, Markus, Tunyasuvunakool, Saran, Siegel, Noah Y., Hafner, Roland, Bloesch, Michael, Hartikainen, Kristian, Byravan, Arunkumar, Hasenclever, Leonard, Tassa, Yuval, Sadeghi, Fereshteh, Batchelor, Nathan, Casarini, Federico, Saliceti, Stefano, Game, Charles, Sreendra, Neil, Patel, Kushal, Gwira, Marlon, Huber, Andrea, Hurley, Nicole, Nori, Francesco, Hadsell, Raia, Heess, Nicolas
We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We use
Externí odkaz:
http://arxiv.org/abs/2304.13653
Autor:
Zhang, Jingwei, Springenberg, Jost Tobias, Byravan, Arunkumar, Hasenclever, Leonard, Abdolmaleki, Abbas, Rao, Dushyant, Heess, Nicolas, Riedmiller, Martin
In this paper we study the problem of learning multi-step dynamics prediction models (jumpy models) from unlabeled experience and their utility for fast inference of (high-level) plans in downstream tasks. In particular we propose to learn a jumpy mo
Externí odkaz:
http://arxiv.org/abs/2302.12617
Autor:
Byravan, Arunkumar, Humplik, Jan, Hasenclever, Leonard, Brussee, Arthur, Nori, Francesco, Haarnoja, Tuomas, Moran, Ben, Bohez, Steven, Sadeghi, Fereshteh, Vujatovic, Bojan, Heess, Nicolas
We present a system for applying sim2real approaches to "in the wild" scenes with realistic visuals, and to policies which rely on active perception using RGB cameras. Given a short video of a static scene collected using a generic phone, we learn th
Externí odkaz:
http://arxiv.org/abs/2210.04932