Market-Based Reinforcement Learning in Partially Observable Worlds
Ivo KweeMarcus HutterJürgen SchmidhuberPublished in: CoRR (2001)
Keyphrases
- partially observable
- reinforcement learning
- state space
- markov decision processes
- partial observability
- partially observable domains
- markov decision problems
- partially observable environments
- partial observations
- dynamical systems
- action models
- function approximation
- decision problems
- model free
- hidden state
- reinforcement learning algorithms
- infinite horizon
- reward function
- machine learning
- multi agent
- belief space
- dynamic programming
- partially observable markov decision process
- optimal control
- temporal difference
- decision making
- learning algorithm
- belief state
- dynamic systems
- optimal policy
- random walk
- linear programming
- fully observable
- action selection