Policies that Generalize: Solving Many Planning Problems with the Same Policy.
Blai BonetHector GeffnerPublished in: IJCAI (2015)
Keyphrases
- planning problems
- markov decision problems
- state space
- partially observable markov decision processes
- optimal policy
- fully observable
- solving planning problems
- heuristic search
- domain independent
- stochastic domains
- markov decision process
- partially observable
- planning domains
- reinforcement learning
- control policies
- reward function
- ai planning
- continuous state
- partial observability
- probabilistic planning
- dynamic programming
- deterministic domains
- linear programming
- infinite horizon
- planning systems
- decision processes
- markov decision processes
- orders of magnitude
- control policy
- policy iteration
- markov chain
- decision theoretic
- finite state
- domain independent planning
- sat encodings
- dynamical systems
- htn planning
- search strategies
- planning graph
- causal graph
- average reward
- initial state
- state variables