microsoft / segar
Sandbox environment for generalizable agent research
☆24Updated 2 years ago
Alternatives and similar repositories for segar:
Users that are interested in segar are comparing it to the libraries listed below
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Updated 4 years ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆22Updated last year
- ☆42Updated 3 years ago
- Learning Action-Value Gradients in Model-based Policy Optimization☆31Updated 3 years ago
- Change-Based Exploration Transfer☆36Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆53Updated 2 years ago
- ☆41Updated last year
- Reward shaping approach for instruction following settings, leveraging language at multiple levels of abstraction.☆19Updated 3 years ago
- Learning Robust Dynamics Through Variational Sparse Gating☆21Updated 2 years ago
- ☆20Updated 2 years ago
- Simplistic Pytorch Implementation of the Dreamer-RL☆20Updated 2 years ago
- JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"☆43Updated 3 years ago
- Invariant Causal Prediction for Block MDPs☆44Updated 4 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆80Updated last year
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆85Updated 3 years ago
- RAD: Reinforcement Learning with Augmented Data (code for procgen experiments)☆18Updated 3 years ago
- ☆39Updated 3 years ago
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)☆23Updated 5 years ago
- Latent World Models For Intrinsically Motivated Exploration | Official repository☆22Updated 3 years ago
- Docker containers of baseline agents for the Crafter environment☆28Updated 3 years ago
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation (ICLR2023)☆13Updated last year
- Implementation of Tactical Optimistic and Pessimistic value estimation☆24Updated last year
- ☆22Updated 2 years ago
- CREATE Environment for long-horizon physics-puzzle tasks with diverse tools☆18Updated 2 years ago
- Reinforcement Learning via Supervised Learning☆69Updated 2 years ago
- Generalised UDRL☆37Updated 2 years ago
- Code for "Possibility Before Utility: Learning And Using Hierarchical Affordances" ICLR 2022☆14Updated 2 years ago
- CaDM: Context-aware Dynamics Model for Generalization in Model-based Reinforcement Learning☆63Updated 4 years ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆85Updated last year
- Revisiting Rainbow☆73Updated 3 years ago