Probabilistic Policy Blending for Shared Autonomy using Deep Reinforcement Learning.
Saurav SinghJamison HeardPublished in: RO-MAN (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- reinforcement learning problems
- reinforcement learning algorithms
- state space
- markov decision processes
- reward function
- action space
- function approximators
- generative model
- function approximation
- policy evaluation
- probabilistic logic
- control policy
- multi agent
- bayesian networks
- control policies
- policy gradient
- actor critic
- state action
- probabilistic model
- state and action spaces
- markov decision problems
- partially observable environments
- partially observable markov decision processes
- uncertain data
- posterior probability
- dynamic programming
- policy iteration
- average reward
- partially observable
- model free
- infinite horizon
- long run
- continuous state spaces
- learning process
- learning algorithm
- neural network