Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Mahajan, Anuj"'
With advances in generative AI, there is increasing work towards creating autonomous agents that can manage daily tasks by operating user interfaces (UIs). While prior research has studied the mechanics of how AI agents might navigate UIs and underst
Externí odkaz:
http://arxiv.org/abs/2410.09006
Autor:
Nayak, Siddharth, Orozco, Adelmo Morrison, Have, Marina Ten, Thirumalai, Vittal, Zhang, Jackson, Chen, Darren, Kapoor, Aditya, Robinson, Eric, Gopalakrishnan, Karthik, Harrison, James, Ichter, Brian, Mahajan, Anuj, Balakrishnan, Hamsa
The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge and handcr
Externí odkaz:
http://arxiv.org/abs/2407.10031
Autor:
Mahajan, Anuj, Zhang, Amy
Learning policies which are robust to changes in the environment are critical for real world deployment of Reinforcement Learning agents. They are also necessary for achieving good generalization across environment shifts. We focus on bisimulation me
Externí odkaz:
http://arxiv.org/abs/2306.04595
Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a
Externí odkaz:
http://arxiv.org/abs/2303.13808
Trust Region Policy Optimization (TRPO) is an iterative method that simultaneously maximizes a surrogate objective and enforces a trust region constraint over consecutive policies in each iteration. The combination of the surrogate objective maximiza
Externí odkaz:
http://arxiv.org/abs/2302.07985
Autor:
Ellis, Benjamin, Cook, Jonathan, Moalla, Skander, Samvelyan, Mikayel, Sun, Mingfei, Mahajan, Anuj, Foerster, Jakob N., Whiteson, Shimon
The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-Agent Challenge (SMAC) has become a popular testbed for centralised tr
Externí odkaz:
http://arxiv.org/abs/2212.07489
A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents
Externí odkaz:
http://arxiv.org/abs/2212.05331
Autor:
Mahajan, Anuj, Samvelyan, Mikayel, Gupta, Tarun, Ellis, Benjamin, Sun, Mingfei, Rocktäschel, Tim, Whiteson, Shimon
Collective intelligence is a fundamental trait shared by several species of living organisms. It has allowed them to thrive in the diverse environmental conditions that exist on our planet. From simple organisations in an ant colony to complex system
Externí odkaz:
http://arxiv.org/abs/2202.00104
Autor:
Mahajan, Anuj, Samvelyan, Mikayel, Mao, Lei, Makoviychuk, Viktor, Garg, Animesh, Kossaifi, Jean, Whiteson, Shimon, Zhu, Yuke, Anandkumar, Animashree
Publikováno v:
2nd Workshop on Quantum Tensor Networks in Machine Learning (NeurIPS 2021)
We present an extended abstract for the previously published work TESSERACT [Mahajan et al., 2021], which proposes a novel solution for Reinforcement Learning (RL) in large, factored action spaces using tensor decompositions. The goal of this abstrac
Externí odkaz:
http://arxiv.org/abs/2110.14538
Publikováno v:
2nd Workshop on Quantum Tensor Networks in Machine Learning (NeurIPS 2021)
A challenge in multi-agent reinforcement learning is to be able to generalize over intractable state-action spaces. Inspired from Tesseract [Mahajan et al., 2021], this position paper investigates generalisation in state-action space over unexplored
Externí odkaz:
http://arxiv.org/abs/2110.14524