Maximum Reward Formulation In Reinforcement Learning.
Sai Krishna GottipatiYashaswi PathakRohan Nuttall SahirRaviteja ChunduruAhmed TouatiSriram Ganapathi SubramanianMatthew E. TaylorSarath ChandarPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- state space
- function approximation
- eligibility traces
- reward function
- markov decision processes
- learning algorithm
- reinforcement learning algorithms
- model free
- partially observable environments
- learning problems
- optimal policy
- long run
- transfer learning
- supervised learning
- learning capabilities
- partially observable
- learning agent
- average reward
- temporal difference learning
- reinforcement learning methods
- approximate dynamic programming
- multi agent
- machine learning
- robotic control
- reward shaping
- continuous state
- temporal difference
- learning classifier systems