alexander-turner / attainable-utility-preservation

Related projects: ⓘ

• neale / avoiding-side-effects
  Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments
  ☆12Updated 3 years ago
• paulfchristiano / amplification
  ☆9Updated 4 years ago
• minqi / wordcraft
  An environment for benchmarking commonsense agents
  ☆28Updated 4 years ago
• PartnershipOnAI / safelife
  SafeLife: safety benchmarks for reinforcement learning agents
  ☆59Updated 3 years ago
• mfranzs / meta-learning-curiosity-algorithms
  ☆80Updated 11 months ago
• uber-research / backpropamine
  Train self-modifying neural networks with neuromodulated plasticity
  ☆77Updated 4 years ago
• ucl-dark / paired
  PAIRED in PyTorch 🔥
  ☆56Updated last year
• 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
• sebastianrisi / ga-world-models
  ☆20Updated 5 years ago
• HumanCompatibleAI / evaluating-rewards
  Library to compare and evaluate reward functions
  ☆61Updated 10 months ago
• HumanCompatibleAI / rlsp
  Reward Learning by Simulating the Past
  ☆43Updated 5 years ago
• adamjermyn / toy_model_interpretability
  ☆10Updated last year
• google-deepmind / dm_hard_eight
  ☆85Updated 3 years ago
• HumanCompatibleAI / interpreting-rewards
  Experiments in applying interpretability techniques to learned reward functions.
  ☆9Updated 3 years ago
• FragileTech / plangym
  Library that provides environments for planning problems
  ☆13Updated 2 weeks ago
• instadeepai / AlphaNPI
  Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.
  ☆77Updated 11 months ago
• uber-research / Map-Elites-Evolutionary
  Map-Elites based on Evolution Strategies
  ☆31Updated 2 years ago
• mtensor / rulesynthesis
  Code for "Learning Compositional Rules via Neural Program Synthesis"
  ☆58Updated 3 years ago
• maciej-sypetkowski / autoascend
  The first place solution for the NeurIPS 2021 Nethack Challenge -- https://www.aicrowd.com/challenges/neurips-2021-the-nethack-challenge
  ☆54Updated last year
• koulanurag / mmn
  Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
  ☆47Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆11Updated 2 years ago
• eaplatanios / jelly-bean-world
  A framework for experimenting with never-ending learning
  ☆72Updated 2 years ago
• andrewschreiber / agent
  Interpretability dashboard for reinforcement learners
  ☆16Updated 5 years ago
• google-deepmind / enn_acme
  ☆29Updated 2 years ago
• samacqua / LARC
  Language-annotated Abstraction and Reasoning Corpus
  ☆76Updated last year
• louiskirsch / vsml-neurips2021
  Code for "Meta Learning Backpropagation And Improving It" @ NeurIPS 2021 https://arxiv.org/abs/2012.14905
  ☆31Updated 2 years ago
• ElisevanderPol / PRAE
  Plannable Approximations to MDP Homomorphisms: Equivariance under Actions
  ☆26Updated 4 years ago
• juliuskunze / cwvae-jax
  Clockwork VAEs in JAX/Flax
  ☆31Updated 3 years ago
• abbyvansoest / maxent
  ☆14Updated 5 years ago
• joschu / jax-exp
  ☆24Updated 5 years ago