Reinforcement Learning Your Way: Agent Characterization through Policy Regularization.
Charl MareeChristian W. OmlinPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- action selection
- markov decision process
- reward function
- agent learns
- state action
- agent receives
- optimal policy
- partially observable
- multi agent
- policy search
- markov decision processes
- state space
- learning agent
- reinforcement learning algorithms
- action space
- intelligent agents
- policy gradient
- temporal difference
- function approximation
- total reward
- decision making
- policy iteration
- agent model
- actor critic
- selective perception
- single agent
- control policy
- function approximators
- multiagent systems
- partially observable environments
- dynamic programming
- model free
- multiple agents
- partially observable markov decision process
- control policies
- exploration strategy
- state and action spaces
- dynamical systems
- infinite horizon
- reinforcement learning problems
- evaluation function
- state abstraction
- reinforcement learning agents
- autonomous learning
- learning capabilities
- markov decision problems
- learning algorithm
- multi agent systems
- learning process
- dynamic environments
- transfer learning
- autonomous agents
- average reward
- learning agents
- multi agent environments
- learning problems
- decision problems
- optimal control
- long run
- expected reward
- machine learning
- policy evaluation