New answers tagged deep-rl
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 ...
1
vote
RL agent for autonomous vehicle is able to follow the road but can't avoid crashing at all (Highway-Env / Racetrack Env.)
There are a few things I think worth looking into:
Is avoiding the other car actually possible in the environment? You may inadvertently be giving the agent a choice of crashing in lane, or going off ...
Top 50 recent answers are included
Related Tags
deep-rl × 503reinforcement-learning × 428
dqn × 158
q-learning × 78
deep-learning × 62
policy-gradients × 31
proximal-policy-optimization × 29
neural-networks × 27
ddpg × 26
experience-replay × 23
actor-critic-methods × 22
rewards × 18
machine-learning × 17
gym × 17
reward-functions × 15
double-dqn × 15
papers × 14
training × 13
reference-request × 13
alphazero × 13
action-spaces × 13
deep-neural-networks × 12
function-approximation × 12
hyper-parameters × 12
reinforce × 12