Dibya Ghosh's repositories
icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
dibyaghosh.github.io
A staging area for potential websites
epistemic_pomdp
Repository for the NeurIPS 2021 paper: "Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
config_spec
A small library to help create JSON-serializable configs for functions and classes
blog
variationalbay.es
google-research
Google Research
level-replay
This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.
octo-anonymous
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
pretrained_vision
Utilities for converting pretrained checkpoints to jaxrl_m compatible format