New answers tagged experience-replay
2
votes
Why is a large replay buffer inefficient?
I read the same thing recently, and my interpretation was this:
If you only use the very-most recent data, you will overfit to that and things will break
We'd like to train the network to predict ...
Top 50 recent answers are included
Related Tags
experience-replay × 44reinforcement-learning × 42
dqn × 19
deep-rl × 18
q-learning × 10
actor-critic-methods × 5
machine-learning × 4
deep-learning × 4
policy-gradients × 3
ddpg × 3
tensorflow × 2
long-short-term-memory × 2
hyper-parameters × 2
off-policy-methods × 2
on-policy-methods × 2
contextual-bandits × 2
neural-networks × 1
comparison × 1
papers × 1
ai-design × 1
function-approximation × 1
policies × 1
environment × 1
gym × 1
statistical-ai × 1