AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay.
Adarsh SehgalMuskan SehgalHung Manh LaPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- optimal control
- neuro fuzzy
- gradient method
- function approximation
- action selection
- policy iteration
- state space
- optimal policy
- average reward
- control problems
- policy gradient methods
- model free
- function approximators
- markov decision processes
- supervised learning
- machine learning
- evaluation function
- real valued
- convergence rate
- action space
- learning problems
- temporal difference learning
- rl algorithms
- sufficient conditions
- objective function