AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset.
Dongsu LeeChanin EomMinhae KwonPublished in: ICRA (2024)
Keyphrases
- reinforcement learning
- autonomous driving
- reinforcement learning algorithms
- function approximation
- grand challenge
- state space
- stereo vision
- learning algorithm
- temporal difference
- machine learning
- rl algorithms
- model free
- real time
- multi agent
- markov decision processes
- direct policy search
- action space
- state and action spaces
- temporal difference learning
- control policy
- markov decision process
- object recognition
- dynamic programming
- learning classifier systems
- optimal policy
- vision algorithms
- multi agent systems
- reinforcement learning methods
- action selection
- high quality
- partially observable domains