dibyaghosh

PhD Student at UC Berkeley | Previously @ Google Brain Montreal

Pinned Repositories

AGI
A PyTorch library for Artificial General Intelligence (AGI)
3 3 01
autogit
Python library for creating periodic git backups of your codebase (e.g. right before launching an experiment).
Language:Python4 3 00
dnc
Code for "Divide-and-Conquer Reinforcement Learning"
Language:Python58 5 112
gcsl
Code for "Learning to Reach Goals via Iterated Supervised Learning"
Language:Python75 7 810
icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
Language:Python78 4 23
jaxrl_m
Skeleton for scalable and flexible Jax RL implementations
Language:Python54 4 00
minecraft-ai
A (now obsolete) API for RL agents in Minecraft
Language:Python9 7 20
remote_gym
Language:Python4 2 00
octo
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
Language:Python645 17 85114
prob140
A Berkeley library for probability theory.
Language:Jupyter Notebook13 4 13

dibyaghosh's Repositories

dibyaghosh/icvf_release
Public code for "Reinforcement Learning from Passive Data via Latent Intentions"
Language:Python78 4 23
dibyaghosh/gcsl
Code for "Learning to Reach Goals via Iterated Supervised Learning"
Language:Python75 7 810
dibyaghosh/jaxrl_m
Skeleton for scalable and flexible Jax RL implementations
Language:Python54 4 00
dibyaghosh/autogit
Python library for creating periodic git backups of your codebase (e.g. right before launching an experiment).
Language:Python4 3 00
dibyaghosh/remote_gym
Language:Python4 2 00
dibyaghosh/codesave
Easy way to save codebases (for later loading!)
Language:Python2 2 0
dibyaghosh/dibyaghosh.github.io
A staging area for potential websites
Language:HTML2 1 00
dibyaghosh/epistemic_pomdp
Repository for the NeurIPS 2021 paper: "Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Language:HTML2 4 1
dibyaghosh/config_spec
A small library to help create JSON-serializable configs for functions and classes
Language:Python1 2 0
dibyaghosh/jaxamine
Basically the Dopamine RL library, but without any TF references
Language:Python1 3 0
dibyaghosh/jaxrl
Language:Jupyter Notebook1 3 0
dibyaghosh/offline_procgen
Language:Python1 3 0
dibyaghosh/offlinerl_adaptation
Language:HTML1 3 0
dibyaghosh/rlutil
Custom version of justinjfu/rlutil
Language:Python1 4 0
dibyaghosh/rtx_viz
Language:HTML1 2 0
dibyaghosh/bairblog.github.io
Language:JavaScript
dibyaghosh/blog
variationalbay.es
Language:Jupyter Notebook
dibyaghosh/coinrun
Language:C++3 0
dibyaghosh/d4rl
A benchmark for offline reinforcement learning.
Language:Python2 0
dibyaghosh/doodad
Language:Python2 0
dibyaghosh/flax_model
Language:Python
dibyaghosh/google-research
Google Research
Language:Jupyter Notebook2 0
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.
Language:Python
dibyaghosh/octo-anonymous
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
Language:Python1 0
dibyaghosh/ppo-ensemble-2
Language:Python3 11
dibyaghosh/pretrained_vision
Utilities for converting pretrained checkpoints to jaxrl_m compatible format
Language:Python2 0
dibyaghosh/procgen
Procgen Benchmark: Procedurally Generated Game-Like Gym Environments
Language:C++2 0
dibyaghosh/testtt
3 0
dibyaghosh/testtt22
3 0
dibyaghosh/tpu_utils
Language:Python