1
vote
How to enforce action bounds between 0 & 1 in soft actor-critic algorithm?
Yes you can map the output onto [0,1] as you indicate. You should treat this as a modification to the environment. I.e. imagine that the environment takes actions in [-1, 1] instead of [0,1]. No you ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
soft-actor-critic × 17reinforcement-learning × 12
deep-rl × 6
actor-critic-methods × 5
td3 × 3
papers × 2
proximal-policy-optimization × 2
off-policy-methods × 2
neural-networks × 1
comparison × 1
tensorflow × 1
q-learning × 1
dqn × 1
objective-functions × 1
optimization × 1
gradient-descent × 1
policy-gradients × 1
proofs × 1
hyperparameter-optimization × 1
value-functions × 1
hyper-parameters × 1
loss × 1
on-policy-methods × 1
continuous-action-spaces × 1
dynamic-programming × 1