|
Polyathlon |
|
|
|
Creators: Adam White and Brian Tanner, University of Alberta; Shimon Whiteson, Universiteit van Amsterdam In the future robots will be used in many homes, offices and construction sites. It would be useful if these robots could learn to perform new tasks on-the-job with little dependance on human guidance and training. The polyathlon is meant to simulate this senerio: the agent faces a series of unknown tasks. The agent must learn, online, how to solve each task without any prior task knowledge or pretraining. The polyathlon raises a number of interesting algorithmic challenges, such as transfer learning, feature construction, adaptive representations and parameter-free learning. The First Annual Reinforcement Learning Competition, at NIPS 2006, featured a pentathlon, where participants were allowed to train there agents on two environments. Agents were tested on five environments including the two known environments and three unknown environments. The team from Rutgers University won the 2006 Pentathlon. Technical DetailsObservation Space: k dimensional, continuous or discrete valued - k will not exceed 20
Action Space: 1 dimensional, discrete valued - small set of descrete actions
Rewards: unknown
Note: the competition software will provide your agent with a task specification string that describes the basic inputs and outputs of the particular problem instance your agent is facing. For the competition, the ranges provided in task specification may not be tight; they provide a rough approximation of the actual observation and action ranges. More documentation of the the task specification string can be found here .
|
|
|
