Improved caching support

HumanCompatibleAI / population-irl

(Experimental) Inverse reinforcement learning from trajectories generated by multiple agents with different (but correlated) rewards

MIT License

26 stars 2 forks source link

Closed AdamGleave closed 6 years ago

AdamGleave commented 6 years ago

Ability to disable caching on a particular run (or other more fine-grained ways of invalidating cached results)
Log when waiting on cached results (sometimes process hangs for a long time waiting on disk, and it's not always clear what's going on)

AdamGleave commented 6 years ago

Mostly addressed by commit 11ac51