brett-daley / gym-classicsLinks
Classic environments for reinforcement learning and dynamic programming, implemented in OpenAI Gym and Gymnasium.
☆21Updated 2 years ago
Alternatives and similar repositories for gym-classics
Users that are interested in gym-classics are comparing it to the libraries listed below
Sorting:
- Benchmarking RL generalization in an interpretable way.☆174Updated last month
- ☆202Updated 2 years ago
- OpenAI Gym wrapper for the DeepMind Control Suite☆226Updated last year
- Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.☆176Updated last year
- ☆324Updated last year
- Gym-like extensions for POMDP☆56Updated 4 years ago
- ☆306Updated 3 years ago
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆321Updated last year
- Partially Observable Process Gym☆211Updated 6 months ago
- Hindsight policy gradients☆46Updated 5 years ago
- ☆359Updated 3 years ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆50Updated last year
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆31Updated 5 years ago
- Unofficial Pytorch code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"☆194Updated 3 years ago
- Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)☆198Updated 2 years ago
- Simple maze environments using mujoco-py☆57Updated 2 years ago
- Simple gym environments for safety in Reinforcement Learning Research☆18Updated last year
- PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tu…☆157Updated 2 years ago
- Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022☆341Updated last year
- A pytorch reprelication of the model-based reinforcement learning algorithm MBPO☆182Updated 3 years ago
- Author's PyTorch implementation of TD7 for online and offline RL☆159Updated 2 years ago
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆38Updated 2 years ago
- Deep Hierarchical Planning from Pixels☆112Updated 3 years ago
- PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)☆253Updated 5 years ago
- NeurIPS Reproducibility Challenge 2019☆20Updated 5 years ago
- Code for MOPO: Model-based Offline Policy Optimization☆191Updated 3 years ago
- Diversity is All You Need: Learning Skills without a Reward Function in PyTorch.☆84Updated 2 years ago
- ☆114Updated 2 years ago
- ☆10Updated 2 years ago
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆22Updated 2 years ago