Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization.
Igor KuznetsovPublished in: AAMAS (2024)
Keyphrases
- monte carlo
- temporal difference
- guided exploration
- reinforcement learning
- monte carlo methods
- stochastic approximation
- actor critic
- function approximation
- markov chain
- monte carlo simulation
- reinforcement learning algorithms
- exploratory learning
- adaptive sampling
- temporal difference learning
- importance sampling
- monte carlo tree search
- policy evaluation
- dynamic programming
- particle filter
- state space
- function approximators
- variance reduction
- evaluation function
- learning algorithm
- quasi monte carlo
- markovian decision