no code implementations • ICML 2020 • Aravind Rajeswaran, Igor Mordatch, Vikash Kumar
We point out that a large class of MBRL algorithms can be viewed as a game between two players: (1) a policy player, which attempts to maximize rewards under the learned model; (2) a model player, which attempts to fit the real-world data collected by the policy player.
no code implementations • 8 May 2024 • Yide Shentu, Philipp Wu, Aravind Rajeswaran, Pieter Abbeel
This enables LLMs to flexibly communicate goals in the task plan without being entirely constrained by language limitations.
no code implementations • 3 Oct 2023 • Sneha Silwal, Karmesh Yadav, Tingfan Wu, Jay Vakil, Arjun Majumdar, Sergio Arnaud, Claire Chen, Vincent-Pierre Berges, Dhruv Batra, Aravind Rajeswaran, Mrinal Kalakrishnan, Franziska Meier, Oleksandr Maksymets
We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks.
1 code implementation • 1 Jun 2023 • Gaoyue Zhou, Victoria Dean, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari, Kyle Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta
Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across labs), and we lack internet-scale robotics data.
1 code implementation • 4 May 2023 • Philipp Wu, Arjun Majumdar, Kevin Stone, Yixin Lin, Igor Mordatch, Pieter Abbeel, Aravind Rajeswaran
We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making.
no code implementations • NeurIPS 2023 • Arjun Majumdar, Karmesh Yadav, Sergio Arnaud, Yecheng Jason Ma, Claire Chen, Sneha Silwal, Aryan Jain, Vincent-Pierre Berges, Pieter Abbeel, Jitendra Malik, Dhruv Batra, Yixin Lin, Oleksandr Maksymets, Aravind Rajeswaran, Franziska Meier
Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average).
no code implementations • 12 Dec 2022 • Zhao Mandi, Homanga Bharadhwaj, Vincent Moens, Shuran Song, Aravind Rajeswaran, Vikash Kumar
On a real robot setup, CACTI enables efficient training of a single policy that can perform 10 manipulation tasks involving kitchen objects, and is robust to varying layouts of distractors.
1 code implementation • 12 Dec 2022 • Nicklas Hansen, Zhecheng Yuan, Yanjie Ze, Tongzhou Mu, Aravind Rajeswaran, Hao Su, Huazhe Xu, Xiaolong Wang
In this paper, we examine the effectiveness of pre-training for visuo-motor control tasks.
1 code implementation • 12 Dec 2022 • Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran
We identify key ingredients for leveraging demonstrations in model learning -- policy pretraining, targeted exploration, and oversampling of demonstration data -- which forms the three phases of our model-based RL framework.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 12 Oct 2022 • Gaoyue Zhou, Liyiming Ke, Siddhartha Srinivasa, Abhinav Gupta, Aravind Rajeswaran, Vikash Kumar
Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience.
no code implementations • 23 Apr 2022 • Yuchen Cui, Scott Niekum, Abhinav Gupta, Vikash Kumar, Aravind Rajeswaran
Task specification is at the core of programming autonomous robots.
1 code implementation • 23 Mar 2022 • Suraj Nair, Aravind Rajeswaran, Vikash Kumar, Chelsea Finn, Abhinav Gupta
We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks.
no code implementations • 10 Mar 2022 • Allan Zhou, Vikash Kumar, Chelsea Finn, Aravind Rajeswaran
Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment.
no code implementations • 7 Mar 2022 • Simone Parisi, Aravind Rajeswaran, Senthil Purushwalkam, Abhinav Gupta
In this context, we revisit and study the role of pre-trained visual representations for control, and in particular representations trained on large-scale computer vision datasets.
1 code implementation • 1 Feb 2022 • Michael Laskin, Hao liu, Xue Bin Peng, Denis Yarats, Aravind Rajeswaran, Pieter Abbeel
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors.
no code implementations • 29 Sep 2021 • Catherine Cang, Kourosh Hakhamaneshi, Ryan Rudes, Igor Mordatch, Aravind Rajeswaran, Pieter Abbeel, Michael Laskin
In this paper, we investigate how we can leverage large reward-free (i. e. task-agnostic) offline datasets of prior interactions to pre-train agents that can then be fine-tuned using a small reward-annotated dataset.
no code implementations • 29 Sep 2021 • Tanmay Shankar, Yixin Lin, Aravind Rajeswaran, Vikash Kumar, Stuart Anderson, Jean Oh
In this paper, we explore how we can endow robots with the ability to learn correspondences between their own skills, and those of morphologically different robots in different domains, in an entirely unsupervised manner.
no code implementations • NeurIPS 2021 • Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn
We consider a setting where an agent is provided a fixed dataset of visual demonstrations illustrating how to perform a task, and must learn to solve the task using the provided demonstrations and unsupervised environment interactions.
no code implementations • 16 Jun 2021 • Catherine Cang, Aravind Rajeswaran, Pieter Abbeel, Michael Laskin
When combined together, they substantially improve the performance and generalization of offline RL policies.
16 code implementations • NeurIPS 2021 • Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch
In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling.
Ranked #3 on Offline RL on D4RL
no code implementations • ICLR Workshop SSL-RL 2021 • Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn
We consider the problem setting of imitation learning where the agent is provided a fixed dataset of demonstrations.
4 code implementations • NeurIPS 2021 • Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran, Sergey Levine, Chelsea Finn
We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-action tuples generated via rollouts under the learned model.
2 code implementations • NeurIPS 2021 • Wenling Shang, Xiaofei Wang, Aravind Srinivas, Aravind Rajeswaran, Yang Gao, Pieter Abbeel, Michael Laskin
Temporal information is essential to learning effective policies with Reinforcement Learning (RL).
1 code implementation • 21 Dec 2020 • Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn
In this work, we build on recent advances in model-based algorithms for offline RL, and extend them to high-dimensional visual observation spaces.
no code implementations • NeurIPS 2020 • Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims
In this work, we present MOReL, an algorithmic framework for model-based offline RL.
2 code implementations • 12 May 2020 • Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims
In this work, we present MOReL, an algorithmic framework for model-based offline RL.
no code implementations • 16 Apr 2020 • Aravind Rajeswaran, Igor Mordatch, Vikash Kumar
Model-based reinforcement learning (MBRL) has recently gained immense interest due to its potential for sample efficiency and ability to incorporate off-policy data.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • L4DC 2020 • Colin Summers, Kendall Lowrey, Aravind Rajeswaran, Siddhartha Srinivasa, Emanuel Todorov
We introduce Lyceum, a high-performance computational ecosystem for robot learning.
6 code implementations • NeurIPS 2019 • Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine
By drawing upon implicit differentiation, we develop the implicit MAML algorithm, which depends only on the solution to the inner level optimization and not the path taken by the inner loop optimizer.
no code implementations • ICLR Workshop LLD 2019 • Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine
Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch.
no code implementations • ICLR 2019 • Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch
We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning.
no code implementations • 14 Oct 2018 • Henry Zhu, Abhishek Gupta, Aravind Rajeswaran, Sergey Levine, Vikash Kumar
Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators.
no code implementations • 28 Mar 2018 • Kendall Lowrey, Svetoslav Kolev, Jeremy Dao, Aravind Rajeswaran, Emanuel Todorov
Reinforcement learning has emerged as a promising methodology for training robot controllers.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • ICLR 2018 • Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M. Bayen, Sham Kakade, Igor Mordatch, Pieter Abbeel
To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP.
1 code implementation • ICLR 2018 • Dibya Ghosh, Avi Singh, Aravind Rajeswaran, Vikash Kumar, Sergey Levine
In this paper, we develop a novel algorithm that instead partitions the initial state space into "slices", and optimizes an ensemble of policies, each on a different slice.
1 code implementation • 28 Sep 2017 • Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, Giulia Vezzani, John Schulman, Emanuel Todorov, Sergey Levine
Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency.
1 code implementation • NeurIPS 2017 • Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham Kakade
This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks.
no code implementations • 5 Oct 2016 • Aravind Rajeswaran, Sarvjeet Ghotra, Balaraman Ravindran, Sergey Levine
Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks.
no code implementations • 9 Sep 2016 • Jayadev P Satya, Nirav Bhatt, Ramkrishna Pasumarthy, Aravind Rajeswaran
In a power distribution network, the network topology information is essential for an efficient operation of the network.
no code implementations • 19 Nov 2015 • P Satya Jayadev, Aravind Rajeswaran, Nirav P Bhatt, Ramkrishna Pasumarthy
Consumers with low demand, like households, are generally supplied single-phase power by connecting their service mains to one of the phases of a distribution transformer.
no code implementations • 1 Jun 2015 • Aravind Rajeswaran, Shankar Narasimhan
We show that identification is equivalent to learning a model $\mathbf{A_n}$ which captures the approximate linear relationships between the different variables comprising $\mathbf{X}$ (i. e. of the form $\mathbf{A_n X \approx 0}$) such that $\mathbf{A_n}$ is full rank (highest possible) and consistent with a network node-edge incidence structure.