Login / Signup
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation.
Boyan Li
Hongyao Tang
Yan Zheng
Jianye Hao
Pengyi Li
Zhen Wang
Zhaopeng Meng
Li Wang
Published in:
CoRR (2021)
Keyphrases
</>
continuous action
policy search
reinforcement learning
continuous state
action space
continuous state and action spaces
state space
partially observable markov decision processes
reinforcement learning algorithms
dynamic programming
control policies
reward function
optimal policy
markov decision processes
function approximation
finite state
reinforcement learning methods
robot navigation
action selection
neural network
real valued
machine learning
model free
markov decision problems
decision problems
learning algorithm