Login / Signup
Deep Reinforcement Learning with Sarsa and Q-Learning: A Hybrid Approach.
Zhixiong Xu
Lei Cao
Xi-liang Chen
Chenxi Li
Yongliang Zhang
Jun Lai
Published in:
IEICE Trans. Inf. Syst. (2018)
Keyphrases
</>
reinforcement learning
reinforcement learning algorithms
function approximation
state space
rl algorithms
model free
temporal difference learning
markov decision processes
eligibility traces
state action space
continuous state and action spaces
mountain car
reinforcement learning problems
temporal difference
multi agent
control problems
function approximators
action selection
supervised learning
tile coding
reinforcement learning methods
policy iteration
learning agent
optimal policy
neural network
learning problems
transfer learning
dynamic programming
learning algorithm
machine learning
continuous state
multi agent reinforcement learning
actor critic
state abstraction
td learning
reward shaping