Improving and Benchmarking Offline Reinforcement Learning Algorithms.
Bingyi KangXiao MaYirui WangYang YueShuicheng YanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- model free
- state space
- markov decision processes
- reinforcement learning problems
- reinforcement learning methods
- eligibility traces
- learning algorithm
- partially observable environments
- function approximation
- stochastic games
- policy search
- temporal difference
- dynamic environments
- reward function
- search space
- multi agent
- training data
- data mining
- reward shaping