AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process.
Kevin DuIan GempYi WuYingying WuPublished in: CoRR (2022)
Keyphrases
- markov decision process
- policy iteration
- np hard
- initial state
- markov decision processes
- finite state
- state space
- optimal policy
- sample path
- reinforcement learning
- special case
- temporal difference learning
- infinite horizon
- optimal solution
- finite horizon
- lower bound
- transition matrices
- average reward
- computational complexity
- situation calculus
- linear programming
- markov games
- factored mdps
- average cost
- approximate solutions
- decision problems
- probability distribution
- action space
- partially observable markov decision processes
- reward function
- function approximation
- long run