-
I'm rerunning velocity baselines in the POMDP directory and I'm observing exploding Q values fairly often. I was wondering if this is something you experienced during training. TD3 seems to avoid over…
-
Hi,
Is it available a benchmark (speed and memory) w.r.t the original **POMCP** **C++** code? It would interesting also for large POMDPs
-
@zsunberg While looking at ways to reduce the size of the action space in my model during computation, I came across the `POMCP.sparse_actions` function in the [documentation](https://juliapomdp.githu…
-
In this pomdp function, it seems that line 146, “function Pb=getPb”, should output variable omega so that omega in line 140 can be defined.
This bug exists in the current codes, please check this …
-
LightDarkPOMDPs.jl:5 uses the command "importall", which was removed in Julia 1.0.
```julia
# __precompile__()
module LightDarkPOMDPs
importall POMDPs #
-
A content ERROR was logged by "a user" at the following url:
https://courses.voll-ki.fau.de/course-notes/ai-1?inDocPath=0
## The issue as described by the user:
```
Content getting collapsed
```
##…
-
Would it be technically possible to have a module in AI-Toolbox capable of loading MDP/POMDP models in [RDDL](https://github.com/ssanner/rddlsim) and/or [PPDDL](https://ipc04.icaps-conference.org/prob…
-
Currently, we have `actionvalues` to get a vector of values, one for each action in the POMDP. Making sure these values always match up to the right actions seems rather error prone; it might be more …
-
This solver uses some function that are broader than the minimal interface defined in RLInterface and relies on internal fields such as `env.problem` in many places.
Ideally, the solver should suppo…
-
👋 I was wondering if there's a reason that [Stochastic] Hill Climbing isn't part of `Optim.jl` – I definitely get that Simulated Annealing is a "better" version of [S]HC, but [S]HC is still useful for…