ReinforcementLearning.jl
ReinforcementLearning.jl copied to clipboard
JuliaReinforcementLearning
A reinforcement learning package for Julia
Hello, I was just wondering if the ReinforcementLearning.jl package can handle Partially Observed MDPs? I know that the POMDP.jl package can work with these, but the interface is very different....
I think we need to pass `traj[:terminal]` to `discount_rewards` so that the gain is computed only up to termination of an episode? https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/blob/6fe6aa01208c325f8f990032621c18b61d574b37/src/ReinforcementLearningZoo/src/algorithms/policy_gradient/vpg.jl#L105
In the website https://juliareinforcementlearning.org/, there are the three lines ```julia julia> ] add ReinforcementLearningExperiments julia> using ReinforcementLearningExperiments julia> run(E`JuliaRL_BasicDQN_CartPole`) ``` However, the third one gives (on Julia v1.7.1) ```julia julia>...
I've started refactoring the DQN implementations, but I'm fairly new to Julia so I'd appreciate your feedback about whether this is a good idea or not. In essence, it looks...
Haven't found any docs about this. Can't figure how to use the following code in src/environments/3rd_party/atari.jl: ```julia imshowgrey(x::AbstractArray{UInt8,2}) = imshowgrey(reshape(x, :), size(x)) imshowgrey(x::AbstractArray{UInt8,1}, dims) = imshow(reshape(x, dims), colormap = 2)...
I only realize this problem very recently. Multiple dispatch seems to be overused here in this package. For example, the `update!` function. I thought it was quite straightforward. When we...
PR Checklist - [ ] Update NEWS.md? Base implementation of [PETS](https://arxiv.org/abs/1805.12114) (see also [facebookresearch/mbrl-lib](https://github.com/facebookresearch/mbrl-lib)) that is currently not working. I might not have a lot of time for this in...
A2C and PPO can be improved further to support mutiple discrete action space
Most deep rl algorithms in RLZoo assume the state to be an array. However, states of a graph or any other data structure should also be supported out of the...
Metadata
Owner
Metadata
A reinforcement learning package for Julia