danijar
Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction
DeepMindBerkeley
Pinned Repositories
crafter
Benchmarking the Spectrum of Agent Capabilities
daydreamer
DayDreamer: World Models for Physical Robot Learning
director
Deep Hierarchical Planning from Pixels
dreamer
Dream to Control: Learning Behaviors by Latent Imagination
dreamerv2
Mastering Atari with Discrete World Models
dreamerv3
Mastering Diverse Domains through World Models
handout
Turn Python scripts into handouts with Markdown and figures
layered
Clean implementation of feed forward neural networks
mindpark
Testbed for deep reinforcement learning
danijar's Repositories
danijar/dreamerv3
Mastering Diverse Domains through World Models
danijar/dreamerv2
Mastering Atari with Discrete World Models
danijar/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
danijar/crafter
Benchmarking the Spectrum of Agent Capabilities
danijar/daydreamer
DayDreamer: World Models for Physical Robot Learning
danijar/director
Deep Hierarchical Planning from Pixels
danijar/ninjax
General Modules for JAX
danijar/embodied
Fast reinforcement learning research
danijar/elements
Building blocks for productive research
danijar/crafter-baselines
Docker containers of baseline agents for the Crafter environment
danijar/diamond_env
Standardized Minecraft Diamond Environment for Reinforcement Learning
danijar/portal
Fast and reliable distributed systems in Python
danijar/granular
Fast dataset format and loader
danijar/teleport
Efficiently send large arrays across machines
danijar/dotfiles
My Linux and Mac configuration
danijar/npgame
Write simple games in Numpy!
danijar/awesome-rl-envs
danijar/imptools
Tools for improving Python imports
danijar/scope
Scalable metrics logging and analysis
danijar/tdmpc2
Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"
danijar/fidjax
Frechet Inception Distance in JAX
danijar/bigym
Demo-Driven Mobile Bi-Manual Manipulation Benchmark.
danijar/minerl
danijar/acme
A library of reinforcement learning components and agents
danijar/conny
Recurrent neural network implementation targeted towards evaluating new topologies
danijar/danijar
danijar/lab
A customisable 3D platform for agent-based AI research
danijar/memory-maze
Memory Maze environment for evaluating long-term memory of RL agents.
danijar/mujoco
Multi-Joint dynamics with Contact. A general purpose physics simulator.
danijar/rich
Rich is a Python library for rich text and beautiful formatting in the terminal.