mazpie / contrastive-aifLinks
[NeurIPS 2021] World modelling and action learning using a contrastive formulation of the active inference framework, for reaching visual goal states
☆14Updated 2 years ago
Alternatives and similar repositories for contrastive-aif
Users that are interested in contrastive-aif are comparing it to the libraries listed below
Sorting:
- ☆26Updated 5 years ago
- Reinforcement Learning through Active Inference☆79Updated 5 years ago
- Deep active inference agents using Monte-Carlo methods☆96Updated 7 months ago
- Code for the paper Deep Active Inference as Variational Policy Gradients.☆27Updated 6 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆161Updated 2 years ago
- Code for "On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning" (TMLR, 2022)☆19Updated 2 years ago
- Tutorials on learning and using successor representations.☆54Updated 6 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆92Updated 4 years ago
- Deep Hierarchical Planning from Pixels☆113Updated 3 years ago
- ☆54Updated 2 years ago
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.☆76Updated 2 years ago
- Unofficial re-implementation of "Learning Latent Dynamics for Planning from Pixels" (https://arxiv.org/abs/1811.04551 ) with PyTorch☆47Updated 5 years ago
- Code for Model-Free Opponent Shaping (ICML 2022)☆20Updated 3 years ago
- Codes for the study "Variational Recurrent Models for Solving Partially Observable Control Tasks", published as a conference paper at ICL…☆55Updated 5 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆82Updated 2 years ago
- Partially Observable Process Gym☆211Updated 7 months ago
- Benchmarking RL generalization in an interpretable way.☆173Updated 2 months ago
- A Library for Active Preference-based Reward Learning Algorithms☆53Updated 2 years ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆109Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆321Updated 2 years ago
- Pytorch version of Dreamer, which follows the original TF v2 codes.☆139Updated 3 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆103Updated 3 years ago
- 🧊 🚩Comparison of active inference, q-learning and bayesian rl using modified FrozenLake environment☆34Updated 5 years ago
- A collection of RL algorithms written in JAX.☆104Updated 3 years ago
- Repository for the paper: "Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation" @ NeurIPS 2022☆21Updated 2 years ago
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning…☆70Updated 2 years ago
- Implementation of the Option-Critic Architecture☆40Updated 7 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆74Updated last year
- ☆115Updated 2 years ago
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS☆29Updated 2 years ago