Controlgym: Large-Scale Safety-Critical Control Environments for Benchmarking Reinforcement Learning Algorithms.
Xiangyuan ZhangWeichao MaoSaviz MowlaviMouhacine BenosmanTamer BasarPublished in: CoRR (2023)
Keyphrases
- reinforcement learning algorithms
- safety critical
- reinforcement learning
- state space
- markov decision processes
- dynamic environments
- model free
- fault tolerant
- embedded systems
- formal methods
- control system
- control problems
- function approximation
- safety analysis
- real time
- reinforcement learning problems
- learning algorithm
- temporal difference
- reward function
- support systems
- monte carlo
- control strategies
- agent architecture
- learning tasks
- adaptive systems
- cooperative
- decision making