Lagrangian Model Based Reinforcement Learning
Dec 2, 2022
Speakers
Adithya Ramesh
Speaker · 0 followers
Balaraman Ravindran
Speaker · 0 followers
About
One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. In robotics, collecting large amounts of training data using actual robots is not practical. One approach to improve the sample efficiency of RL algorithms is model-based RL. Here we learn a model of the environment, essentially its transition dynamics and reward function, and use it to generate imaginary trajectories, which we then use to update the policy. Intuitively, learning better environment models should improve model-based RL. Recently there has been growing interest in developing better deep neural network based dynamics models for physical systems through better inductive biases. We investigate if such physics-informed dynamics models can also improve model-based RL. We focus on robotic systems undergoing rigid body motion. We utilize the structure of rigid body dynamics to learn Lagrangian neural networks and use them within a model-based RL algorithm. We find that our Lagrangian model-based RL approach achieves better average-return and sample efficiency compared to standard model-based RL as well as state-of-the-art model-free RL algorithms such as Soft-Actor-Critic, in complex environments.One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. In robotics, collecting large amounts of training data using actual robots is not practical. One approach to improve the sample efficiency of RL algorithms is model-based RL. Here we learn a model of the environment, essentially its transition dynamics and reward function, and use it to generate imaginary trajectories, which we then use to update the policy. Intuitively, learning better environment models sh…
Organizer
NeurIPS 2022
Account · 961 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
Watch later
Penghao Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Lightweight Prompt Learning with General Representation for Rehearsal-free Continual Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
De Novo Protein Design
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Exploring the Relationship Between Model Prediction Uncertainty and Gradient Inversion Attack Vulnerability for Federated Learning-Based Diabetic Retinopathy Grade Classification
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
Watch later
Shiyun Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning
Watch later
Jianda Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%