1 code implementation • 2 May 2024 • Darshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar
In the real world, the strong episode resetting mechanisms that are needed to train agents in simulation are unavailable.
no code implementations • 30 Jan 2024 • Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing.
1 code implementation • 20 Jan 2024 • Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Based on this analysis, we construct new datasets to explicitly test for this property, revealing that SL-based methods lack this stitching property and hence fail to perform combinatorial generalization.
1 code implementation • 27 Oct 2023 • Roger Creus Castanyer, Joshua Romoff, Glen Berseth
Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary and hence are difficult to optimize for the agent.
no code implementations • 4 Oct 2023 • Raj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, Glen Berseth
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs.
1 code implementation • 12 Sep 2023 • Siddarth Venkatraman, Shivesh Khaitan, Ravi Tej Akella, John Dolan, Jeff Schneider, Glen Berseth
However, a key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset while avoiding extrapolation errors arising due to a lack of support in the dataset.
no code implementations • 7 Sep 2023 • Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
We further evaluate on a simulated Sawyer pushing task with eye gaze control, and the Lunar Lander game with simulated user commands, and find that our method improves over baseline interfaces in these domains as well.
no code implementations • 19 Feb 2023 • Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world.
no code implementations • 1 Aug 2022 • Yandong Ji, Zhongyu Li, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing algorithms to enable a legged robot to shoot a soccer ball to a given target is a challenging problem that combines robot motion control and planning into one task.
no code implementations • 17 Jun 2022 • Brandon Trabucco, Mariano Phielipp, Glen Berseth
Ours is the first reinforcement learning algorithm that can train a policy to generalize to new agent morphologies without requiring a description of the agent's morphology in advance.
no code implementations • 4 Mar 2022 • Jensen Gao, Siddharth Reddy, Glen Berseth, Nicholas Hardy, Nikhilesh Natraj, Karunesh Ganguly, Anca D. Dragan, Sergey Levine
In the typing domain, we leverage backspaces as feedback that the interface did not perform the desired action.
no code implementations • 5 Feb 2022 • Sean Chen, Jensen Gao, Siddharth Reddy, Glen Berseth, Anca D. Dragan, Sergey Levine
Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e. g., webcam images of eye gaze) can be challenging, especially when it involves inferring the user's desired action in the absence of a natural 'default' interface.
no code implementations • ICLR 2022 • Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, Sergey Levine
Beyond simply transferring past experience to new tasks, our goal is to devise continual reinforcement learning algorithms that learn to learn, using their experience on previous tasks to learn new tasks more quickly.
no code implementations • NeurIPS 2021 • Nicholas Rhinehart, Jenny Wang, Glen Berseth, John D. Co-Reyes, Danijar Hafner, Chelsea Finn, Sergey Levine
We study this question in dynamic partially-observed environments, and argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model.
no code implementations • 28 Jul 2021 • Charles Sun, Jędrzej Orbik, Coline Devin, Brian Yang, Abhishek Gupta, Glen Berseth, Sergey Levine
Our aim is to devise a robotic reinforcement learning system for learning navigation and manipulation together, in an autonomous way without human intervention, enabling continual learning under realistic assumptions.
1 code implementation • ICML Workshop URL 2021 • Arnaud Fickinger, Natasha Jaques, Samyak Parajuli, Michael Chang, Nicholas Rhinehart, Glen Berseth, Stuart Russell, Sergey Levine
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering.
no code implementations • ICML Workshop URL 2021 • Nicholas Rhinehart, Jenny Wang, Glen Berseth, John D Co-Reyes, Danijar Hafner, Chelsea Finn, Sergey Levine
We study this question in dynamic partially-observed environments, and argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model.
no code implementations • 23 Apr 2021 • Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair, Alexander Khazatsky, Glen Berseth, Sergey Levine
Contextual policies provide this capability in principle, but the representation of the context determines the degree of generalization and expressivity.
no code implementations • 26 Mar 2021 • Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing robust walking controllers for bipedal robots is a challenging endeavor.
no code implementations • ICLR Workshop Learning_to_Learn 2021 • John D Co-Reyes, Sarah Feng, Glen Berseth, Jie Qui, Sergey Levine
Current reinforcement learning algorithms struggle to quickly adapt to new situations without large amounts of experience and usually without large amounts of optimization over that experience.
no code implementations • ICLR 2021 • Jensen Gao, Siddharth Reddy, Glen Berseth, Nicholas Hardy, Nikhilesh Natraj, Karunesh Ganguly, Anca Dragan, Sergey Levine
In the typing domain, we leverage backspaces as implicit feedback that the interface did not perform the desired action.
no code implementations • 1 Jan 2021 • Glen Berseth, Florian Golemo, Christopher Pal
It would be desirable for a reinforcement learning (RL) based agent to learn behaviour by merely watching a demonstration.
no code implementations • 22 Jun 2020 • John D. Co-Reyes, Suvansh Sanjeev, Glen Berseth, Abhishek Gupta, Sergey Levine
Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions.
no code implementations • 31 Dec 2019 • Brian Yang, Dinesh Jayaraman, Glen Berseth, Alexei Efros, Sergey Levine
Existing approaches for visuomotor robotic control typically require characterizing the robot in advance by calibrating the camera or performing system identification.
1 code implementation • ICLR 2021 • Glen Berseth, Daniel Geng, Coline Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche.
1 code implementation • 5 Dec 2019 • Abdul Rahman Kreidieh, Glen Berseth, Brandon Trabucco, Samyak Parajuli, Sergey Levine, Alexandre M. Bayen
This allows us to draw on connections between communication and cooperation in multi-agent RL, and demonstrate the benefits of increased cooperation between sub-policies on the training performance of the overall policy.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • 23 Oct 2019 • Ashvin Nair, Shikhar Bahl, Alexander Khazatsky, Vitchyr Pong, Glen Berseth, Sergey Levine
When the robot's environment and available objects vary, as they do in most open-world settings, the robot must propose to itself only those goals that it can accomplish in its present setting with the objects that are at hand.
no code implementations • 25 Sep 2019 • Glen Berseth, Daniel Geng, Coline Devin, Dinesh Jayaraman, Chelsea Finn, Sergey Levine
All living organisms struggle against the forces of nature to carve out niches where they can maintain relative stasis.
Unsupervised Pre-training Unsupervised Reinforcement Learning
no code implementations • 25 Sep 2019 • Glen Berseth, Brandon haworth, Seonghyeon Moon, Mubbasir Kapadia, Petros Faloutsos
Multi-agent reinforcement learning is a particularly challenging problem.
no code implementations • 22 Jan 2019 • Glen Berseth, Florian Golemo, Christopher Pal
We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration.
no code implementations • 27 Sep 2018 • Glen Berseth, Christopher J. Pal
In this paper we propose an approach using only visual information to learn a distance metric between agent behaviour and a given video demonstration.
1 code implementation • 17 Apr 2018 • Glen Berseth, Xue Bin Peng, Michiel Van de Panne
We provide $89$ challenging simulation environments that range in difficulty.
3 code implementations • 15 Mar 2018 • Zhaoming Xie, Glen Berseth, Patrick Clary, Jonathan Hurst, Michiel Van de Panne
By formulating a feedback control problem as finding the optimal policy for a Markov Decision Process, we are able to learn robust walking controllers that imitate a reference motion with DRL.
Robotics
no code implementations • ICLR 2018 • Glen Berseth, Cheng Xie, Paul Cernek, Michiel Van de Panne
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment.
no code implementations • 11 Jan 2018 • Glen Berseth, Michiel Van de Panne
Deep reinforcement learning has achieved great strides in solving challenging motion control tasks.