Interactive Reinforcement Learning with Inaccurate Feedback
| Autor: | Taylor Kessler Faulkner, Andrea L. Thomaz, Elaine Schaertl Short |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Process (engineering)
Computer science business.industry media_common.quotation_subject 02 engineering and technology 010501 environmental sciences 01 natural sciences 0202 electrical engineering electronic engineering information engineering Robot Reinforcement learning 020201 artificial intelligence & image processing Quality (business) Artificial intelligence business Baseline (configuration management) Advice (complexity) 0105 earth and related environmental sciences media_common |
| Zdroj: | ICRA |
| DOI: | 10.1109/icra40945.2020.9197219 |
| Popis: | Interactive Reinforcement Learning (RL) enables agents to learn from two sources: rewards taken from observations of the environment, and feedback or advice from a secondary critic source, such as human teachers or sensor feedback. The addition of information from a critic during the learning process allows the agents to learn more quickly than non-interactive RL. There are many methods that allow policy feedback or advice to be combined with RL. However, critics can often give imperfect information. In this work, we introduce a framework for characterizing Interactive RL methods with imperfect teachers and propose an algorithm, Revision Estimation from Partially Incorrect Resources (REPaIR), which can estimate corrections to imperfect feedback over time. We run experiments both in simulations and demonstrate performance on a physical robot, and find that when baseline algorithms do not have prior information on the exact quality of a feedback source, using REPaIR matches or improves the expected performance of these algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|