MemRL
Paper: “MEMRL: SELF-EVOLVING AGENTS VIA RUNTIME REINFORCEMENT LEARNING ON EPISODIC MEMORY” Open-Source Code
File Explorer
- buggy_contract.yml
- buggy_test.yml
- config.yml
- model_eval_request.yml
- bcb_subset.py
- get_results.py
- lib2domain.json
- task2domain.json
- utils.py
- __init__.py
- _special_oracle.py
- utils.py
- __init__.py
- anthropic_request.py
- google_request.py
- hf_inference_request.py
- mistral_request.py
- openai_request.py
- __init__.py
- __init__.py
- anthropic.py
- base.py
- google.py
- hf.py
- hf_inference.py
- mistral.py
- openai.py
- utility.py
- vllm.py
- __init__.py
- evaluate.py
- generate.py
- inspect.py
- sanitize.py
- syncheck.py
- n_gram_check.py
- odex_10_overlap.txt
- odex_13_overlap.txt
- stackoverflow_10_overlap.txt
- stackoverflow_13_overlap.txt
- starcoderdata_10_overlap.txt
- Evaluate.Dockerfile
- Generate.Dockerfile
- Gradio.Dockerfile
- requirements-eval.txt
- requirements.txt
- e2b.Dockerfile
- e2b.toml
- requirements.txt
- test_legacy_sanitizer.py
- test_treesitter_sanitizer.py
- fix_v019.py
- fix_v020.py
- fix_v022.py
- fix_v023.py
- fix_v025.py
- .dockerignore
- .gitignore
- .pre-commit-config.yaml
- ADVANCED_USAGE.md
- CITATION.cff
- LICENSE
- MANIFEST.in
- pyproject.toml
- README.md
- README_MEMRL_VENDOR.md
- release.sh
- release_docker.sh
- run.sh
- setup.cfg
- forwarding_app.md
- server_control_app.md
- shutdown_server.md
- start_server.md
- default
- forwarding_app.sh
- hfd.sh
- kill_docker.sh
- run_mypy.sh
- __init__.py
- fixed_response_agent.py
- language_model_agent.py
- oracle_agent.py
- __init__.py
- agent.py
- __init__.py
- consecutive_abnormal_agent_inference_process_handling_callback.py
- current_session_saving_callback.py
- group_self_consistency_callback.py
- previous_sample_utilization_callback.py
- __init__.py
- callback.py
- constructor.py
- restorer.py
- main.py
- __init__.py
- main.py
- utility.py
- run_experiment_remotely.py
- shutdown_server.py
- start_server.py
- construct.py
- task_requirement.py
- __init__.py
- chat_history_item_factory.py
- client.py
- server.py
- __init__.py
- config_factory.py
- __init__.py
- __init__.py
- huggingface_language_model.py
- openai_language_model.py
- __init__.py
- language_model.py
- __init__.py
- container.py
- task.py
- logic_form_util.py
- semantic_parser_util.py
- sparql_executor.py
- __init__.py
- api.py
- task.py
- __init__.py
- container.py
- task.py
- utility.py
- __init__.py
- task.py
- text_environment.py
- utility.py
- __init__.py
- __init__.py
- client.py
- server.py
- task.py
- __init__.py
- config.py
- exception.py
- general.py
- instance_factory.py
- request.py
- response.py
- session.py
- status.py
- __init__.py
- client.py
- color_message.py
- config_loader.py
- logger.py
- retry.py
- server.py
- main.py
- run_experiment.py
- test_client_server.py
- .gitignore
- pyproject.toml
- README.md
- requirements.txt
- alfworld_examples.json
- full_seed123.json
- hard_seed42.json
- alfworld.yaml
- rl_alf_config.yaml
- rl_bcb_config.yaml
- rl_hle_config.yaml
- rl_llb_config.yaml
- full_seed123.json
- bigcodebench_full.jsonl
- db_bench_data.json
- db_bench_runtime_learning_data.json
- db_train.json
- db_val.json
- os_interaction_data.json
- os_interaction_runtime_learning_data.json
- os_interaction_train.json
- os_interaction_val.json
- __init__.py
- base.py
- history.py
- memp_agent.py
- prompts.py
- __init__.py
- bcb_adapter.py
- eval_utils.py
- task_wrappers.py
- __init__.py
- main.py
- __init__.py
- config.py
- __init__.py
- alfworld_env.py
- base.py
- __init__.py
- lm_adapter.py
- memory_context.py
- prompts.py
- sanitize.py
- task_wrappers.py
- __init__.py
- base.py
- embedding.py
- llm.py
- __init__.py
- alfworld_rl_runner.py
- base_runner.py
- bcb_runner.py
- hle_runner.py
- llb_rl_runner.py
- __init__.py
- builders.py
- keyer.py
- memory_service.py
- procedural_memory.py
- retrievers.py
- strategies.py
- updater.py
- value_driven.py
- __init__.py
- llb_jsonl.py
- tracing_llm.py
- __init__.py
- task_id.py
- __init__.py
- __version__.py
- spec.md
- .openspec.yaml
- design.md
- proposal.md
- tasks.md
- spec.md
- config.yaml
- run_alfworld.py
- run_bcb.py
- run_hle.py
- run_llb.py
- merge_llb_train_val.py
- test_sim_threshold.py
- .gitignore
- framework_overview.pdf
- framework_overview.png
- LICENSE
- pyproject.toml
- README.md
- requirements.txt
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Command Glossary
Commands referenced in this DOCs, explained below.
conda activate
View Details ▼
conda activate
Activate a conda environment.
See also: `conda deactivate`.
conda activate myenv
Activate an existing environment named `myenv`:
conda activate {{path/to/myenv}}
Activate an existing environment located at custom path:
conda activate --stack myenv
Stack `myenv` environment on top of a previous environment making libraries/commands/variables from both accessible:
conda create
View Details ▼
conda create
Create new conda environments.
conda create {{[-y|--yes]}} {{[-n|--name]}} py39 python=3.9 "numpy>=1.11" scipy
Create a new environment named `py39`, install Python 3.9, NumPy v1.11 or above in it, and the latest stable version of SciPy. Say yes to all confirmations:
conda create {{[-n|--name]}} myenv --file {{file1.yml}} --file {{file2.yml}}
Create a new environment named `myenv` and install packages listed in files:
conda create {{[-p|--prefix]}} {{path/to/myenv}}
Create a new environment at a custom path (i.e. prefix):
pip install
View Details ▼
pip install
Install Python packages.
pip install {{package1 package2 ...}}
Install one or more packages:
pip install {{package1 package2 ...}} {{[-U|--upgrade]}}
Upgrade all specified packages to the latest version, installing any that are not already present:
pip install {{package}}=={{version}}
Install a specific version of a package:
python
View Details ▼
python
Python language interpreter.
python
Start a REPL (interactive shell):
python {{path/to/file.py}}
Execute a specific Python file:
python -i {{path/to/file.py}}
Execute a specific Python file and start a REPL: