yhs0602 / CraftGround
โกโก Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecraft ๐๏ธ
โ49Updated last week
Alternatives and similar repositories for CraftGround:
Users that are interested in CraftGround are comparing it to the libraries listed below
- Goal-Conditioned Reinforcement Learning with JAXโ142Updated 3 weeks ago
- Deep Hierarchical Planning from Pixelsโ96Updated 2 years ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)โ68Updated last year
- Evaluating long-term memory of reinforcement learning algorithmsโ141Updated last year
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023โ19Updated last year
- โ81Updated 2 months ago
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELSโ25Updated last year
- โ18Updated 2 months ago
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"โ42Updated last week
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)โ80Updated 4 months ago
- Skeleton for scalable and flexible Jax RL implementationsโ80Updated last year
- ExORL: Exploratory Data for Offline Reinforcement Learningโ112Updated 3 years ago
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observationsโ100Updated 10 months ago
- Official implementation of the BRO algorithmโ42Updated 2 months ago
- Foundation Policies with Hilbert Representations (ICML 2024)โ83Updated last year
- Simple maze environments using mujoco-pyโ54Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU settingโ156Updated last month
- Challenging Memory-based Deep Reinforcement Learning Agentsโ97Updated 5 months ago
- A Simplified Pytorch Version of the Dreamer Algorithmโ126Updated last year
- A benchmark for offline goal-conditioned RL and offline RLโ154Updated 3 weeks ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"โ55Updated last year
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.โ30Updated 4 years ago
- Synthetic Experience Replayโ91Updated 10 months ago
- COOM: Benchmarking Continual Reinforcement Learning on Doomโ17Updated 2 months ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.โ89Updated 2 weeks ago
- [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and โฆโ37Updated last year
- Learning Laplacian Representations in Reinforcement Learningโ17Updated 4 years ago
- a simple and scalable agent for training adaptive policies with sequence-based RLโ119Updated this week
- Conservative Q learning in Jaxโ53Updated 2 years ago
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.โ23Updated last year