Learning Agents with Prioritization and Parameter Noise in Continuous State and Action Space.
Rajesh MangannavarGopalakrishnan SrinivasaraghavanPublished in: ISNN (1) (2019)
Keyphrases
- action space
- continuous state
- learning agents
- reinforcement learning
- single agent
- state space
- multi agent
- markov decision processes
- real valued
- learning agent
- control policies
- decision problems
- continuous state spaces
- dynamic environments
- function approximation
- multiple agents
- state action
- multi agent systems
- stochastic processes
- robot navigation
- path finding
- continuous action
- reinforcement learning algorithms
- action selection
- learning capabilities
- reward function
- heuristic search
- optimal policy
- markov chain
- markov decision process
- temporal difference
- state dependent
- finite state
- planning problems