TheMTank / cups-rl
Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"
☆48Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for cups-rl
- accompanying code for neurips submission "Goal-conditioned Imitation Learning"☆67Updated last year
- Official codebase for LEAP: Planning with Goal Conditioned Policies☆50Updated 2 years ago
- The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)☆75Updated 11 months ago
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control☆137Updated 2 years ago
- Code and project page for D-REX algorithm from the paper "Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrat…☆49Updated last year
- A standalone library to randomize various OpenAI Gym Environments☆60Updated 5 years ago
- Code for "Divide-and-Conquer Reinforcement Learning"☆60Updated 5 years ago
- Residual policy learning☆58Updated 5 years ago
- Code for Environment Probing Interaction Policies [ICLR 2019]☆29Updated 5 years ago
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)☆23Updated 5 years ago
- ☆25Updated last year
- DHER: Hindsight Experience Replay for Dynamic Goals (ICLR-2019)☆66Updated 5 years ago
- Learning to Coordinate Manipulation Skills via Skill Behavior Diversification (ICLR 2020)☆43Updated 2 years ago
- ☆68Updated 3 years ago
- Implementation of CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning☆27Updated 4 years ago
- ☆21Updated 2 years ago
- cordial-sync is a software package than can be used to reproduce the results from the paper "A Cordial Sync: Going Beyond Marginal Polici…☆37Updated 3 years ago
- ☆54Updated 8 months ago
- ☆62Updated 4 years ago
- Energy-Based Hindsight Experience Prioritization (CoRL 2018) Oral presentation (7%)☆33Updated 5 years ago
- Code repository for Active Domain Randomization (CoRL 2019, https://arxiv.org/abs/1904.04762)☆96Updated 3 years ago
- Change-Based Exploration Transfer☆36Updated 2 years ago
- ☆107Updated 4 years ago
- RoboTHOR Challenge☆81Updated 3 years ago
- Repository for the paper "Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors"☆44Updated 2 years ago
- rllab's viskit with some added features☆73Updated last year
- Generalizable Imitation Learning from Observation via Inferring Goal Proximity (NeurIPS 2021)☆22Updated 3 years ago
- Source code for our NIPS 2017 paper, InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations☆42Updated 7 years ago
- Implementation of the skill discovery algorithm described in ICLR submission "Option Discovery using Deep Skill Chaining"☆28Updated 5 years ago
- ☆25Updated 4 years ago