Sparse reward processes

12 years 2 months ago

Download arxiv.org

We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Consequently, the agent is intrinsically motivated to explore its environment beyond the degree necessary to solve the current task it has at hand. We develop a decision theoretic setting that generalises standard reinforcement learning tasks and captures this intuition. More precisely, we consider a multi-stage stochastic game between a learning agent and an opponent. We posit that the setting is a good model for the problem of life-long learning in uncertain environments, where while resources must be spent learning about currently important tasks, there is also the need to allocate effort towards learning about aspects of the world which are not relevant at the moment. This is due to the fact that unpredictable future events may lead to ...

Christos Dimitrakakis

Real-time Traffic

Computer Science | Curiosity & Interest | Decision Making | Game Theory | Machine Learning | Markov Decision Processes | Multitask Learning | Reinforcement Learning |

posted by olethros

» Using Linear Programming for Bayesian Exploration in Markov Decision Processes

» Markov Decision Processes with Arbitrary Reward Processes

» Thresholded Rewards Acting Optimally in Timed ZeroSum Games

» Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning

» Learning from Reinforcement and Advice Using Composite Reward Functions

» Perceptive Evaluation for the Optimal Discounted Reward in Markov Decision Processes

» Pseudometrics for State Aggregation in Average Reward Markov Decision Processes

» Bounded Parameter Markov Decision Processes with Average Reward Criterion

Post Info
More Details (n/a)

Added	24 Jan 2012
Updated	24 Jan 2012
Type	Technical Report
Year	2012
Where	arXiv:1201.255
Authors	Christos Dimitrakakis

Comments (0)

	Complexity of Stochastic Branch and Bound Methods for Belief Tree Search in Bayesian Reinforcement Learning 509 views
	Reid et al.'s Distance Bounding Protocol and Mafia Fraud Attacks over Noisy Channels 545 views
	Rollout Sampling Approximate Policy Iteration 334 views
	Bayesian variable order Markov models. 404 views
	Statistical Decision Making for Authentication and Intrusion Detection 634 views

Sciweavers

Sparse reward processes

Computer Science | Curiosity & Interest | Decision Making | Game Theory | Machine Learning | Markov Decision Processes | Multitask Learning | Reinforcement Learning |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers