Temporal consistency loss & Ape-X DQfD
An algorithm consists of three components: the transformed Bellman operator, the temporal consistency (TC) loss and the combination of Ape-X DQN and DQfD to learn a more consistent human-level policy. ...
My-Rl
MuZero
AlphaZero
Multi-agent Deep Deterministic Policy Gradient
Maximum Entropy Reinforcement Learning via Soft Q-learning & Soft Actor-Critic
Notes on Entropy-Regularized Reinforcement Learning via SQL & SAC ...
Deterministic Policy Gradients
Notes on Deterministic Policy Gradient algorithms ...
Trust Region Policy Optimization
Notes on policy optimization using trust region method. ...