mazpie / contrastive-aif
[NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.
☆11Updated last year
Alternatives and similar repositories for contrastive-aif:
Users that are interested in contrastive-aif are comparing it to the libraries listed below
- ☆24Updated 4 years ago
- Code for the paper Deep Active Inference as Variational Policy Gradients.☆23Updated 5 years ago
- Reinforcement Learning through Active Inference☆69Updated 4 years ago
- Continual RL with wold models☆13Updated last year
- Deep active inference agents using Monte-Carlo methods☆86Updated 3 years ago
- Code for "On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning" (TMLR, 2022)☆14Updated last year
- Codes for the study "Variational Recurrent Models for Solving Partially Observable Control Tasks", published as a conference paper at ICL…☆51Updated 4 years ago
- ☆16Updated 10 months ago
- 🧊 🚩Comparison of active inference, q-learning and bayesian rl using modified FrozenLake environment☆34Updated 4 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆138Updated last year
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆80Updated last year
- This repository is a collection of widely used self-supervised auxiliary losses used for learning representations in reinforcement learni…☆14Updated last year
- Unofficial re-implementation of "Learning Latent Dynamics for Planning from Pixels" (https://arxiv.org/abs/1811.04551 ) with PyTorch☆44Updated 4 years ago
- Code for Model-Free Opponent Shaping (ICML 2022)☆16Updated 2 years ago
- A short conceptual replication of "Prefrontal cortex as a meta-reinforcement learning system" in Jax.☆15Updated last year
- Implementation of the DreamerV2 agent in torch☆14Updated 2 years ago
- Official release of CompoSuite, a compositional RL benchmark☆47Updated last year
- Pytorch code for "Learning Belief Representations for Imitation Learning in POMDPs" (UAI 2019)☆18Updated 2 years ago
- Code for our NeurIPS 2021 paper: Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains☆22Updated 2 years ago
- Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"☆43Updated 2 years ago
- Simple maze environments using mujoco-py☆54Updated last year
- Pytorch version of Dreamer, which follows the original TF v2 codes.☆121Updated 2 years ago
- Synthetic Experience Replay☆84Updated 8 months ago
- Official Implementation for the paper "R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models"☆40Updated 3 months ago
- ☆35Updated 3 years ago
- Learning Off-Policy with Online Planning [CoRL 2021 Best Paper Finalist]☆36Updated 2 years ago
- Inverse Reinforcement Learning via State Marginal Matching, CoRL 2020☆44Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆69Updated 5 months ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆85Updated last year
- Object Centric Atari games☆63Updated this week