Alternatives and similar repositories for attainable-utility-preservation:

Users that are interested in attainable-utility-preservation are comparing it to the libraries listed below

• neale / avoiding-side-effects
  Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments
  ☆12Updated 3 years ago
• minqi / wordcraft
  An environment for benchmarking commonsense agents
  ☆28Updated 4 years ago
• paulfchristiano / amplification
  ☆9Updated 5 years ago
• PartnershipOnAI / safelife
  SafeLife: safety benchmarks for reinforcement learning agents
  ☆60Updated 3 years ago
• ucl-dark / paired
  PAIRED in PyTorch 🔥
  ☆59Updated 2 years ago
• mfranzs / meta-learning-curiosity-algorithms
  ☆80Updated last year
• HumanCompatibleAI / rlsp
  Reward Learning by Simulating the Past
  ☆44Updated 6 years ago
• instadeepai / AlphaNPI
  Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.
  ☆79Updated last year
• HumanCompatibleAI / interpreting-rewards
  Experiments in applying interpretability techniques to learned reward functions.
  ☆10Updated 4 years ago
• sebastianrisi / ga-world-models
  ☆20Updated 5 years ago
• facebookresearch / adversarially-motivated-intrinsic-goals
  This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".
  ☆61Updated last year
• trishullab / houdini
  HOUDINI: Lifelong Learning as Program Synthesis
  ☆48Updated last month
• crunchiness / lernd
  Lernd is ∂ILP (dILP) framework implementation based on Deepmind's paper Learning Explanatory Rules from Noisy Data.
  ☆25Updated 2 years ago
• google-deepmind / dm_hard_eight
  ☆85Updated 4 years ago
• joschu / jax-exp
  ☆24Updated 6 years ago
• HumanCompatibleAI / evaluating-rewards
  Library to compare and evaluate reward functions
  ☆66Updated last year
• juliuskunze / cwvae-jax
  Clockwork VAEs in JAX/Flax
  ☆32Updated 3 years ago
• HumanCompatibleAI / learning_biases
  Infer how suboptimal agents are suboptimal while planning, for example if they are hyperbolic time discounters.
  ☆24Updated 4 years ago
• justinjfu / doodad
  A job launching library for docker, EC2, GCP, etc.
  ☆57Updated 3 years ago
• RichardEvans / apperception
  ☆79Updated 4 years ago
• andrewschreiber / agent
  Interpretability dashboard for reinforcement learners
  ☆16Updated 5 years ago
• uber-research / Map-Elites-Evolutionary
  Map-Elites based on Evolution Strategies
  ☆31Updated 3 years ago
• paulfchristiano / alba
  Implementation of https://medium.com/ai-control/alba-an-explicit-proposal-for-aligned-ai-17a55f60bbcf
  ☆27Updated 7 years ago
• mtensor / rulesynthesis
  Code for "Learning Compositional Rules via Neural Program Synthesis"
  ☆60Updated 4 years ago
• agentmodels / webppl-agents
  Webppl library for generating Gridworld MDPs. JS library for displaying Gridworld.
  ☆22Updated 8 years ago
• facebookresearch / measuring-emergent-comm
  On the pitfalls of measuring emergent communication
  ☆34Updated 6 years ago
• 51alg / TerpreT
  ☆43Updated 7 years ago
• 921kiyo / symbolic-rl
  Symbolic Reinforcement Learning using Inductive Logic Programming
  ☆62Updated 2 years ago
• ElisevanderPol / PRAE
  Plannable Approximations to MDP Homomorphisms: Equivariance under Actions
  ☆30Updated 4 years ago
• google-research / policy-learning-landscape
  Explore the optimization landscape for direct policy learning reinforcement learning.
  ☆50Updated 6 years ago