Pinned Repositories
AGI
A PyTorch library for Artificial General Intelligence (AGI)
autogit
Python library for creating periodic git backups of your codebase (e.g. right before launching an experiment).
dnc
Code for "Divide-and-Conquer Reinforcement Learning"
gcsl
Code for "Learning to Reach Goals via Iterated Supervised Learning"
icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
jaxrl_m
Skeleton for scalable and flexible Jax RL implementations
minecraft-ai
A (now obsolete) API for RL agents in Minecraft
remote_gym
octo
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
prob140
A Berkeley library for probability theory.
dibyaghosh's Repositories
dibyaghosh/icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
dibyaghosh/gcsl
Code for "Learning to Reach Goals via Iterated Supervised Learning"
dibyaghosh/jaxrl_m
Skeleton for scalable and flexible Jax RL implementations
dibyaghosh/autogit
Python library for creating periodic git backups of your codebase (e.g. right before launching an experiment).
dibyaghosh/remote_gym
dibyaghosh/codesave
Easy way to save codebases (for later loading!)
dibyaghosh/dibyaghosh.github.io
A staging area for potential websites
dibyaghosh/epistemic_pomdp
Repository for the NeurIPS 2021 paper: "Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
dibyaghosh/config_spec
A small library to help create JSON-serializable configs for functions and classes
dibyaghosh/jaxamine
Basically the Dopamine RL library, but without any TF references
dibyaghosh/jaxrl
dibyaghosh/offline_procgen
dibyaghosh/offlinerl_adaptation
dibyaghosh/rlutil
Custom version of justinjfu/rlutil
dibyaghosh/rtx_viz
dibyaghosh/bairblog.github.io
dibyaghosh/blog
variationalbay.es
dibyaghosh/coinrun
dibyaghosh/d4rl
A benchmark for offline reinforcement learning.
dibyaghosh/flax_model
dibyaghosh/google-research
Google Research
dibyaghosh/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.
dibyaghosh/models
Models and examples built with TensorFlow
dibyaghosh/octo-anonymous
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
dibyaghosh/ppo-ensemble-2
dibyaghosh/pretrained_vision
Utilities for converting pretrained checkpoints to jaxrl_m compatible format
dibyaghosh/procgen
Procgen Benchmark: Procedurally Generated Game-Like Gym Environments
dibyaghosh/testtt
dibyaghosh/testtt22
dibyaghosh/tpu_utils