Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- partially observable environments
- partially observable
- reward function
- function approximation
- policy iteration
- markov decision processes
- function approximators
- reinforcement learning algorithms
- reinforcement learning problems
- policy gradient
- actor critic
- control policies
- markov decision problems
- approximate dynamic programming
- state and action spaces
- temporal difference
- policy evaluation
- state space
- model free
- long run
- continuous state
- action space
- infinite horizon
- multi agent
- control policy
- decision problems
- model free reinforcement learning
- dynamic programming
- partially observable markov decision processes
- state action
- learning algorithm
- learning capabilities
- continuous state spaces
- inverse reinforcement learning
- multi agent systems
- learning problems
- policy gradient methods
- partially observable domains
- approximate policy iteration
- optimal control
- eligibility traces
- learning classifier systems
- transfer learning
- rl algorithms
- multi agent reinforcement learning
- control problems
- reinforcement learning methods