Marginal Utility for Planning in Continuous or Large Discrete Action Spaces.
Zaheen Farraz AhmadLevi H. S. LelisMichael BowlingPublished in: CoRR (2020)
Keyphrases
- continuous action
- action space
- marginal utility
- continuous state spaces
- state space
- continuous state
- action selection
- partially observable markov decision processes
- policy search
- planning problems
- reinforcement learning
- real valued
- reinforcement learning problems
- markov decision processes
- heuristic search
- control policies
- single agent
- state and action spaces
- markov decision problems
- stochastic processes
- continuous domains
- reinforcement learning algorithms
- cooperative
- optimal policy
- decision making
- finite state
- mobile robot
- search algorithm
- state variables
- finite number
- motion planning
- domain independent