Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation.
Niklas FunkCharles B. SchaffRishabh MadanTakuma YonedaJulen Urain De JesusJoe WatsonEthan K. GordonFelix WidmaierStefan BauerSiddhartha S. SrinivasaTapomayukh BhattacharjeeMatthew R. WalterJan PetersPublished in: CoRR (2021)
Keyphrases
- object manipulation
- real world
- optimal policy
- robot control
- robotic systems
- manipulation tasks
- management policies
- control policies
- allocation policy
- control policy
- markov decision process
- partially observable markov decision processes
- reward function
- dynamic programming
- evolutionary algorithm
- reinforcement learning
- learning algorithm