tinkoff-ai / ReBRAC
Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC
☆50Updated last year
Related projects: ⓘ
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆38Updated last year
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆64Updated last year
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023☆50Updated last year
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆36Updated last month
- An Open-Ended Agentic Simulator☆17Updated last month
- Official implementation for "Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size", NeurIPS 2022, Offline RL Worksho…☆21Updated last year
- ☆25Updated last week
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆27Updated last week
- Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"☆24Updated 7 months ago
- Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022☆28Updated 2 years ago
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC☆11Updated 10 months ago
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆46Updated 3 months ago
- ☆17Updated 3 months ago
- ☆14Updated last month
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS☆20Updated 11 months ago
- Corax: Core RL in JAX☆30Updated 6 months ago
- Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, O…☆12Updated last year
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆26Updated last month
- ☆11Updated 2 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code☆20Updated 3 weeks ago
- ☆56Updated 3 weeks ago
- Synthetic Experience Replay☆62Updated 3 months ago
- Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023☆42Updated 4 months ago
- ☆12Updated last year
- ☆45Updated 5 months ago
- Official code for "World Models via Policy-Guided Trajectory Diffusion", TMLR 2024☆53Updated 5 months ago
- Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observ…☆25Updated last year
- ☆23Updated 10 months ago