New answers tagged proximal-policy-optimization
0
votes
Why clip the PPO objective on only one side?
Quote from https://huggingface.co/learn/deep-rl-course/unit8/visualize :
We update our policy only if:
Our ratio is in the range
Our ratio is outside the range, but the advantage leads to getting ...
Top 50 recent answers are included
Related Tags
proximal-policy-optimization × 105reinforcement-learning × 88
deep-rl × 29
policy-gradients × 20
actor-critic-methods × 11
continuous-action-spaces × 8
on-policy-methods × 7
rewards × 6
soft-actor-critic × 6
trust-region-policy-optimization × 6
dqn × 4
objective-functions × 4
implementation × 4
probability-distribution × 4
neural-networks × 3
deep-learning × 3
comparison × 3
python × 3
reference-request × 3
papers × 3
gym × 3
discrete-action-spaces × 3
training × 2
keras × 2
long-short-term-memory × 2