Imitation Bootstrapped Reinforcement Learning
November 03, 2023 ยท Declared Dead ยท ๐ Robotics: Science and Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Hengyuan Hu, Suvir Mirchandani, Dorsa Sadigh
arXiv ID
2311.02198
Category
cs.LG: Machine Learning
Cross-listed
cs.AI
Citations
53
Venue
Robotics: Science and Systems
Last Checked
3 months ago
Abstract
Despite the considerable potential of reinforcement learning (RL), robotic control tasks predominantly rely on imitation learning (IL) due to its better sample efficiency. However, it is costly to collect comprehensive expert demonstrations that enable IL to generalize to all possible scenarios, and any distribution shift would require recollecting data for finetuning. Therefore, RL is appealing if it can build upon IL as an efficient autonomous self-improvement procedure. We propose imitation bootstrapped reinforcement learning (IBRL), a novel framework for sample-efficient RL with demonstrations that first trains an IL policy on the provided demonstrations and then uses it to propose alternative actions for both online exploration and bootstrapping target values. Compared to prior works that oversample the demonstrations or regularize RL with an additional imitation loss, IBRL is able to utilize high quality actions from IL policies since the beginning of training, which greatly accelerates exploration and training efficiency. We evaluate IBRL on 6 simulation and 3 real-world tasks spanning various difficulty levels. IBRL significantly outperforms prior methods and the improvement is particularly more prominent in harder tasks.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
๐ป
Ghosted
Semi-Supervised Classification with Graph Convolutional Networks
R.I.P.
๐ป
Ghosted
Proximal Policy Optimization Algorithms
R.I.P.
๐ป
Ghosted
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
R.I.P.
๐ป
Ghosted
A Unified Approach to Interpreting Model Predictions
R.I.P.
๐ป
Ghosted