New answers tagged proximal-policy-optimization
0
votes
How to model a multi-agent reinforcement learning problem where actions of different agents can take different durations?
" ... how I would be able to model a multi-agent reinforcement learning problem when each agent performing an action would take different durations to complete the action.
... where vehicles on a ...
1
vote
Accepted
PPO custom implementation: do metrics like value loss, actor loss and entropy move a certain way?
It's difficult to tell how the output of the loss changes over the course of the experiment as you use them as a measure on how well your model performs. Ideally, the loss decreases over time with ...
2
votes
Why is training longer not better in reinforcement learning?
Could it be due to catastrophic forgetting/interference? If once the agent reaches 320K steps it becomes good at the task, it might start to experience only success. This could cause the agent to ...
0
votes
Accepted
How does PPO account for the last reward?
I actually feel kinda dumb writing this, but the update is made if the TOTAL environment steps is a multiple of the time horizon. I did, recode my PPO algorithm, and it seems to eventually solve the ...
Top 50 recent answers are included
Related Tags
proximal-policy-optimization × 73reinforcement-learning × 67
policy-gradients × 20
deep-rl × 12
actor-critic-methods × 10
continuous-action-spaces × 7
trust-region-policy-optimization × 6
implementation × 5
on-policy-methods × 5
deep-learning × 4
objective-functions × 4
rewards × 4
reference-request × 3
python × 3
probability-distribution × 3
action-spaces × 3
neural-networks × 2
papers × 2
keras × 2
hyperparameter-optimization × 2
value-functions × 2
gym × 2
importance-sampling × 2
soft-actor-critic × 2
normal-distribution × 2