mdcrosby / animal-ai
Animal-AI 3
β63Updated last year
Related projects: β
- PAIRED in PyTorch π₯β56Updated last year
- Tutorials on learning and using successor representations.β49Updated 4 years ago
- β53Updated 2 years ago
- Evaluating long-term memory of reinforcement learning algorithmsβ129Updated last year
- Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Explorationβ27Updated 3 years ago
- General Modules for JAXβ57Updated last month
- β16Updated this week
- PushWorld: A benchmark for manipulation planning with tools and movable obstaclesβ75Updated 4 months ago
- Simplistic Pytorch Implementation of the Dreamer-RLβ20Updated 2 years ago
- Train self-modifying neural networks with neuromodulated plasticityβ77Updated 4 years ago
- This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".β61Updated last year
- β85Updated 3 years ago
- Animal-AI supports interdisciplinary research to help better understand human, animal, and artificial cognition.β53Updated last week
- Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686β130Updated 3 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β49Updated 2 years ago
- π§ π©Comparison of active inference, q-learning and bayesian rl using modified FrozenLake environmentβ35Updated 4 years ago
- krazy grid worldβ25Updated 4 years ago
- Episodic Controlβ19Updated 2 years ago
- Code to reproduce Neural Game Engine experiments and pre-trained modelsβ40Updated 2 years ago
- impact-driven-explorationβ125Updated 11 months ago
- Deep active inference agents using Monte-Carlo methodsβ79Updated 2 years ago
- Code for the paper Deep Active Inference as Variational Policy Gradients.β23Updated 4 years ago
- Reinforcement Learning through Active Inferenceβ64Updated 4 years ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according β¦β35Updated 3 months ago
- A collection of RL algorithms written in JAX.β92Updated 2 years ago
- Object Centric Atari gamesβ43Updated this week
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the β¦β83Updated 3 years ago
- [NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"β113Updated 4 years ago
- β34Updated last year
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancyβ13Updated 2 months ago