infer-actively/pymdp
A Python implementation of active inference for Markov Decision Processes
PythonMIT
Issues
- 0
`smoothing_ovf` cannot handle B_dependencies
#156 opened by conorheins - 0
- 1
Agent.infer_states() - Jax not working
#153 opened by aandriella - 0
Test effect of default mctx search policy on multi-cue foraging for SI demos
#150 opened by conorheins - 1
Make tests run against local code, fix syntax warning breaking coverage, and add code coverage generation to github actions
#142 opened by scott-carroll-verses-ai - 1
Consider shifting from raw print statements to using canonical logging
#141 opened by scott-carroll-verses-ai - 0
Not sure linting step in github actions is doing what it was expected to do..
#138 opened by scott-carroll-verses-ai - 2
- 0
Fix `pymdp.utils.obj_array_from_list`
#130 opened by conorheins - 1
an error in the official documentation
#125 opened by Sangxiaofu - 0
- 1
- 2
Choose random action if all action probabilities are the same, even if sampling is deterministic (i.e., some tolerance of probability)
#115 opened by conorheins - 0
Fix assertion when whether `num_controls` is consistent with actions enumerated in policy space
#118 opened by conorheins - 3
! pip install inferactively-pymdp
#113 opened by vala1958 - 1
B matrix navigation problem
#77 opened by thanos927 - 0
Allow learning of likelihood and transition likelihood parameters with sequences of hidden state posteriors
#109 opened by conorheins - 5
Habit learning and precision
#100 opened by PetrAnokhin - 4
einsum while calculating free energy
#98 opened by lqiang2003cn - 2
Sampling action when using deep policy
#99 opened by sunghwan87 - 0
Move plot functions from explicit definition in demos to `utils` module, change axes tick labels calls
#96 opened by conorheins - 1
Allow `alpha` (action precision) to be passed into `Agent()` constructor as optional argument
#81 opened by conorheins - 1
- 1
Error when using `stochastic` mode action sampling in case that `num_controls[f] = 1`
#86 opened by conorheins - 1
Allow direct sampling / selection from posterior over policies, rather than only from posterior over actions
#87 opened by conorheins - 2
Error happend when using update_B()
#91 opened by xugami - 4
State inference: Considerable performance difference with MATLAB implementation?
#82 opened by SamGijsen - 0
Better error messages for MMP
#83 opened by conorheins - 2
- 1
transition matrix B form
#53 opened by mklingebiel - 4
- 1
Typos in Tutorial 1
#71 opened by patrickmineault - 6
Index Error
#33 opened by osaaso3 - 2
A matrix stub bug
#39 opened by conorheins - 4
- 2
Note Arxiv reference
#64 opened by impredicative - 1
Full API documentation
#67 opened by seankmartin - 2
- 0
- 3
- 0
README badges
#68 opened by seankmartin - 1
Polish tutorial 2
#72 opened by patrickmineault