SocNavGym: A Reinforcement Learning Gym for Social Navigation.
Aditya KapoorSushant SwamyLuis MansoPilar BachillerPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- markov decision processes
- dynamic programming
- optimal control
- robotic control
- multi agent
- direct policy search
- control problems
- temporal difference
- model free
- transfer learning
- optimal policy
- machine learning
- markov chain
- evolutionary algorithm
- partially observable
- learning process
- function approximators
- temporal difference learning
- continuous state
- multi agent reinforcement learning
- transition model
- databases