Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning.
Zhifeng QianMingyu YouHongjun ZhouXuanhui XuBin HePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- goal state
- function approximation
- partially observable
- macro actions
- action selection
- stochastic domains
- mixed initiative
- multi agent
- heuristic search
- reinforcement learning algorithms
- transitive closure
- multi agent reinforcement learning
- temporal difference learning
- markov decision process
- neural network
- domain specific
- decision making
- learning algorithm