New answers tagged off-policy-methods
1
vote
Accepted
Has there been a study done in tuning hyper-parameters for off-policy reinforcement learning?
Yes and we can do it in a similar way we normally perform hyper-param optimization. See this paper from Google
In this framework we can also attempt to jerry-rig some of our classic algorithmic tuning ...
Top 50 recent answers are included
Related Tags
off-policy-methods × 59reinforcement-learning × 56
importance-sampling × 17
on-policy-methods × 13
q-learning × 9
policies × 7
monte-carlo-methods × 6
sutton-barto × 6
comparison × 5
deep-rl × 5
dqn × 5
policy-gradients × 5
temporal-difference-methods × 5
sarsa × 5
actor-critic-methods × 4
terminology × 3
proofs × 3
value-functions × 3
ddpg × 2
experience-replay × 2
model-free-methods × 2
exploration-strategies × 2
soft-actor-critic × 2
batch-learning × 2
reference-request × 1