New answers tagged continuous-action-spaces
0
votes
RL - Can RL be applied to problems where the next state is not the next observation?
Yes, there are RL algorithms (dreamer v1,2,3) that predict world model to simulate what (h_t+1) given its sampled action and previous state (h_t). It runs simulated world model during critic-actor so ...
- 101
Top 50 recent answers are included
Related Tags
continuous-action-spaces × 30reinforcement-learning × 26
proximal-policy-optimization × 8
continuous-state-spaces × 8
deep-rl × 6
policy-gradients × 6
dqn × 3
ddpg × 3
reinforce × 3
discrete-action-spaces × 3
deep-learning × 2
markov-decision-process × 2
multi-agent-systems × 2
state-spaces × 2
algorithm-request × 2
action-spaces × 2
multi-armed-bandits × 2
neural-networks × 1
q-learning × 1
terminology × 1
reference-request × 1
papers × 1
objective-functions × 1
deep-neural-networks × 1
monte-carlo-tree-search × 1