New answers tagged policy-gradients
0
votes
Does the policy search work if there is no state to state dependency through actions?
You could save yourself some time and use a contextual bandit solver in the first place if you are secure in your knowledge that the player's actions have no impact on the game state. There is a ...
Top 50 recent answers are included
Related Tags
policy-gradients × 160reinforcement-learning × 144
deep-rl × 25
reinforce × 24
actor-critic-methods × 19
proximal-policy-optimization × 19
neural-networks × 14
ddpg × 13
machine-learning × 7
deep-learning × 7
comparison × 7
objective-functions × 7
rewards × 7
math × 6
pytorch × 6
proofs × 6
sutton-barto × 6
continuous-action-spaces × 6
trust-region-policy-optimization × 6
python × 5
policies × 5
off-policy-methods × 5
multi-agent-systems × 5
advantage-actor-critic × 5
q-learning × 4