tinkoff-ai / eopLinks
Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022
☆28Updated 3 years ago
Alternatives and similar repositories for eop
Users that are interested in eop are comparing it to the libraries listed below
Sorting:
- Official implementation for "Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size", NeurIPS 2022, Offline RL Worksho…☆21Updated 2 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆52Updated 2 years ago
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆75Updated 2 years ago
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆40Updated 2 years ago
- Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023☆53Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 3 years ago
- Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC☆55Updated 2 years ago
- ☆57Updated 6 months ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆103Updated 10 months ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according …☆35Updated last year
- Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"☆31Updated 11 months ago
- JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️☆298Updated this week
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆26Updated 2 years ago
- Baselines for gymnax 🤖☆71Updated 2 years ago
- Pointax: PointMaze Environment for JAX☆24Updated 2 months ago
- ☆19Updated 3 months ago
- Revisiting Rainbow☆75Updated 4 years ago
- Learning Laplacian Representations in Reinforcement Learning☆17Updated 4 years ago
- ☆46Updated 2 years ago
- Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.☆13Updated last year
- CREATE Environment for long-horizon physics-puzzle tasks with diverse tools☆18Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆58Updated 3 years ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆18Updated 10 months ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆48Updated last year
- Evaluating long-term memory of reinforcement learning algorithms☆146Updated 2 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆80Updated 2 years ago
- On the model-based stochastic value gradient for continuous reinforcement learning☆55Updated 2 years ago
- Conservative Q learning in Jax☆54Updated 2 years ago
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆23Updated last year
- ☆19Updated 2 years ago