A hybrid agent called RMC, adding an RNN world model and a decaying curiosity reward to Soft Actor-Critic, is presented with performance claims over SAC, TD3, PPO, and DDPG that are not quantitatively documented.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Reinforcement learning with world model
A hybrid agent called RMC, adding an RNN world model and a decaying curiosity reward to Soft Actor-Critic, is presented with performance claims over SAC, TD3, PPO, and DDPG that are not quantitatively documented.